© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 87828
    Prev
    Next
    INDEX
    Explanations

    Third

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    🧸
    -0.08
    Tu
    -0.07
    cá
    -0.07
     Exclude
    -0.07
    自主
    -0.07
     لهذا
    -0.07
    HB
    -0.07
    十分
    -0.07
     Beverly
    -0.07
    缓
    -0.07
    POSITIVE LOGITS
     growth
    0.08
     sonra
    0.07
    eddar
    0.07
    ㈬
    0.07
     לראות
    0.06
    껭
    0.06
    enade
    0.06
     forces
    0.06
     WIDTH
    0.06
    grown
    0.06
    Activations Density 0.000%

    No Known Activations