© 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. 17349
    Prev
    Next
    INDEX
    Explanations

    reference

    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
    Cour
    -0.07
    ✊
    -0.07
     rainbow
    -0.06
    职业
    -0.06
     SCH
    -0.06
     Felix
    -0.06
    の方が
    -0.06
     Nut
    -0.06
    ձ
    -0.06
     Điều
    -0.06
    POSITIVE LOGITS
     regulating
    0.09
     zwłaszcza
    0.07
     introducing
    0.07
     Wouldn
    0.07
    תכנ
    0.07
     regulated
    0.07
    (jScrollPane
    0.07
    ,message
    0.07
     roślin
    0.07
    liked
    0.07
    Activations Density 0.001%

    No Known Activations