© 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. 15-RESID-POST-AA
    11. 26586
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    subword fragments inside long compound or concatenated tokens (e.g., technical identifiers, usernames, German compounds, or encoding artifacts).

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Channel
    -0.08
    	extern
    -0.07
    搞好
    -0.07
    ’e
    -0.07
     każdym
    -0.07
     happily
    -0.07
     question
    -0.07
     loudly
    -0.07
     CONSTANT
    -0.07
    .less
    -0.07
    POSITIVE LOGITS
    ometrics
    0.09
     PriorityQueue
    0.07
     IReadOnly
    0.07
     Colts
    0.07
     Salem
    0.07
     Slovak
    0.07
     נוס
    0.06
     masterpiece
    0.06
    💠
    0.06
    🍫
    0.06
    Activations Density 0.144%

    No Known Activations