© 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 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. 74959
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    一道
    -0.07
    <Point
    -0.07
     chromium
    -0.07
     mundial
    -0.07
     últimos
    -0.07
     preferably
    -0.07
    $request
    -0.07
    chi
    -0.06
    Ensure
    -0.06
    천
    -0.06
    POSITIVE LOGITS
     BM
    0.07
    /en
    0.07
    _MM
    0.07
    /cm
    0.07
     QA
    0.07
    OLT
    0.07
     inn
    0.06
    AtA
    0.06
     CART
    0.06
    .cat
    0.06
    Activations Density 0.069%

    No Known Activations