© 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. 82790
    Prev
    Next
    INDEX
    Explanations

    code characters

    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
     reconstruction
    -0.07
    酐
    -0.07
    CppGenericClass
    -0.07
    新股
    -0.07
     Ron
    -0.06
     compiler
    -0.06
     surgeons
    -0.06
    rng
    -0.06
    俊
    -0.06
    댘
    -0.06
    POSITIVE LOGITS
     maternal
    0.07
    .vn
    0.07
    refresh
    0.07
    凿
    0.07
     relatives
    0.07
    零
    0.07
    .Areas
    0.07
     OWNER
    0.07
    熠
    0.06
    㧟
    0.06
    Activations Density 0.015%

    No Known Activations