© 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. 4746
    Prev
    Next
    INDEX
    Explanations

    instructions and recommendations

    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
    BH
    -0.07
    个月内
    -0.07
     validity
    -0.06
    产品经理
    -0.06
     '),
    -0.06
     restore
    -0.06
    ('^
    -0.06
     titan
    -0.06
    ﰁ
    -0.06
    ervisor
    -0.06
    POSITIVE LOGITS
     tabel
    0.07
     På
    0.07
     güven
    0.07
    蜩
    0.07
     customary
    0.06
     الو
    0.06
    optic
    0.06
     tread
    0.06
    Paren
    0.06
     pains
    0.06
    Activations Density 0.195%

    No Known Activations