© 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. 15-RESID-POST-AA
    11. 17125
    Prev
    Next
    INDEX
    Explanations

    in-depth articles

    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_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
     courteous
    -0.08
     ek
    -0.07
    .dropdown
    -0.07
    Pure
    -0.07
    religious
    -0.07
     undis
    -0.07
    rowse
    -0.07
    Ak
    -0.07
    .flag
    -0.07
     hv
    -0.07
    POSITIVE LOGITS
     Burton
    0.07
    עמ
    0.07
    升学
    0.07
    جائ
    0.07
     הנאשם
    0.07
     "',
    0.07
     puede
    0.07
    �
    0.07
    のように
    0.07
    �
    0.07
    Activations Density 0.003%

    No Known Activations