© 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. 11-RESID-POST-AA
    11. 107744
    Prev
    Next
    INDEX
    Explanations

    downward direction

    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
    我想
    -0.07
    本赛季
    -0.07
    Saga
    -0.07
    .classes
    -0.06
     stigma
    -0.06
    ☬
    -0.06
    你觉得
    -0.06
    lient
    -0.06
    trait
    -0.06
    POSITIVE LOGITS
    一刀
    0.07
    squ
    0.07
     rune
    0.06
    ribly
    0.06
    pton
    0.06
    ⁄
    0.06
    曹操
    0.06
    坡
    0.06
     rk
    0.06
     PCB
    0.06
    Activations Density 0.022%

    No Known Activations