© 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. 19805
    Prev
    Next
    INDEX
    Explanations

    possessive

    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
    o
    -0.08
     Chapters
    -0.07
    ADMIN
    -0.07
    内部控制
    -0.07
     Alma
    -0.07
    耰
    -0.07
    زو
    -0.07
     deter
    -0.07
    Cream
    -0.07
    مرض
    -0.07
    POSITIVE LOGITS
    比亚
    0.07
    .requests
    0.07
     deadlines
    0.06
    .statusStrip
    0.06
    (indent
    0.06
    גבול
    0.06
     standout
    0.06
     doit
    0.06
     robert
    0.06
    .concatenate
    0.06
    Activations Density 0.015%

    No Known Activations