© 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. 72804
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     stroll
    -0.07
    表
    -0.07
    Dto
    -0.07
    丸
    -0.07
    קל
    -0.07
    .Exec
    -0.07
    ect
    -0.07
    alarm
    -0.06
    幽
    -0.06
    Toe
    -0.06
    POSITIVE LOGITS
    (scope
    0.07
    ᶏ
    0.07
    {↵↵↵
    0.07
     avez
    0.07
    빙
    0.07
    Using
    0.07
    Building
    0.06
    -P
    0.06
    snippet
    0.06
     Options
    0.06
    Activations Density 0.362%

    No Known Activations