© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 49389
    Prev
    Next
    INDEX
    Explanations

    recipes and garnish

    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
    eps
    -0.08
     dear
    -0.07
    !")
    ↵
    -0.07
     sings
    -0.07
     Plays
    -0.07
    .support
    -0.07
     Fiction
    -0.07
    烟火
    -0.07
    enght
    -0.06
    话剧
    -0.06
    POSITIVE LOGITS
     Balance
    0.06
    ROI
    0.06
     skal
    0.06
     (%
    0.06
     QC
    0.06
    _decode
    0.06
     Brook
    0.06
    _GT
    0.06
     Carlo
    0.06
    oho
    0.06
    Activations Density 0.030%

    No Known Activations