© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 65695
    Prev
    Next
    INDEX
    Explanations

    Code and licenses

    np_max-act · gemini-2.0-flash

    The neuron detects document-structure and metadata markers — i.e., headings, section titles/numbers, license/copyright blocks and other formatted metadata or sectioning tokens.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     newPath
    -0.07
    婕
    -0.07
     commanding
    -0.06
    [event
    -0.06
    ;}
    -0.06
     Locations
    -0.06
    Were
    -0.06
    node
    -0.06
    넗
    -0.06
    Ŗ
    -0.06
    POSITIVE LOGITS
    .Mock
    0.07
    .low
    0.06
    博士学位
    0.06
     csak
    0.06
    ('').
    0.06
    -Free
    0.06
     cousin
    0.06
     brom
    0.06
    ('/',
    0.06
    蛋糕
    0.06
    Activations Density 2.339%

    No Known Activations