© 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. 70847
    Prev
    Next
    INDEX
    Explanations

    tm

    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
    登录
    -0.08
     hi
    -0.07
    work
    -0.07
     Key
    -0.07
    Ban
    -0.07
    哈
    -0.07
    事實
    -0.07
    	sl
    -0.07
    pid
    -0.07
     donor
    -0.07
    POSITIVE LOGITS
     Cameras
    0.09
    させて頂
    0.08
    willReturn
    0.07
    尽情
    0.07
     теле
    0.07
    BufferData
    0.07
    这一天
    0.07
    Directive
    0.07
    ResponseBody
    0.06
    ὓ
    0.06
    Activations Density 0.003%

    No Known Activations