© 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. 121389
    Prev
    Next
    INDEX
    Explanations

    study

    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
    1
    -0.15
    ↵↵
    -0.14
    .↵↵
    -0.13
    .↵
    -0.13
     of
    -0.11
    \n
    -0.11
    的
    -0.11
    ↵
    -0.10
    。↵
    -0.10
    ↵
    -0.10
    POSITIVE LOGITS
     Agr
    0.07
    披
    0.07
    孩子们
    0.07
    报记者
    0.07
    帨
    0.06
    Brian
    0.06
    .ReadFile
    0.06
    Pwd
    0.06
    akk
    0.06
    大蒜
    0.06
    Activations Density 0.264%

    No Known Activations