© 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. 86218
    Prev
    Next
    INDEX
    Explanations

    accentuate

    np_max-act · gemini-2.0-flash
    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
    ☒
    -0.08
    çon
    -0.07
    illy
    -0.07
     calle
    -0.07
    晚饭
    -0.07
    钬
    -0.07
    isons
    -0.07
    鸡蛋
    -0.07
    ello
    -0.06
     goo
    -0.06
    POSITIVE LOGITS
     github
    0.07
    _Width
    0.07
     MLA
    0.07
    街道
    0.07
     Creator
    0.07
    /u
    0.07
     propia
    0.07
     uri
    0.06
     repeat
    0.06
     cầm
    0.06
    Activations Density 0.010%

    No Known Activations