© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 126809
    Prev
    Next
    INDEX
    Explanations

    ,

    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
     doping
    -0.07
    Add
    -0.07
    /pkg
    -0.07
     Image
    -0.07
     addAction
    -0.06
    ปวด
    -0.06
     yet
    -0.06
     record
    -0.06
     RELEASE
    -0.06
    elling
    -0.06
    POSITIVE LOGITS
    小伙伴们
    0.08
    宁静
    0.07
     Variables
    0.07
     roy
    0.07
    猫咪
    0.07
    semi
    0.07
     refin
    0.07
    など
    0.07
    啪
    0.07
     essentials
    0.07
    Activations Density 0.132%

    No Known Activations