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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 7-RESID-POST-AA
    11. 81590
    Prev
    Next
    INDEX
    Explanations

    claudication

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -mon
    -0.07
    .snp
    -0.07
    _as
    -0.07
    身心
    -0.07
    -prev
    -0.07
    嚣
    -0.07
     mou
    -0.07
     позв
    -0.07
    quipment
    -0.07
    /app
    -0.07
    POSITIVE LOGITS
     Francisco
    0.08
    Gradient
    0.07
    Until
    0.07
    Act
    0.07
     Manuel
    0.07
     he
    0.06
    ']['
    0.06
     watched
    0.06
     Transaction
    0.06
     Famous
    0.06
    Activations Density 0.002%

    No Known Activations