© 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. 51093
    Prev
    Next
    INDEX
    Explanations

    _type

    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
    厢
    -0.07
     careful
    -0.07
    根本就不
    -0.06
    腐蚀
    -0.06
    缺失
    -0.06
    两名
    -0.06
    瞫
    -0.06
    听着
    -0.06
    cpt
    -0.06
    被害人
    -0.06
    POSITIVE LOGITS
     ¥
    0.09
    ﭵ
    0.07
     Santa
    0.07
    Avatar
    0.07
    anka
    0.07
     Dropbox
    0.07
    すると
    0.07
    忉
    0.07
    Santa
    0.06
    יני
    0.06
    Activations Density 0.000%

    No Known Activations