© 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. 15-RESID-POST-AA
    11. 2603
    Prev
    Next
    INDEX
    Explanations

    Providing resources or tools

    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
     municipal
    -0.07
    ⏤
    -0.07
    하며
    -0.07
    民主生活
    -0.07
    /problem
    -0.07
    具有一定
    -0.07
    ivo
    -0.07
     לתת
    -0.07
    )[
    -0.07
     sher
    -0.07
    POSITIVE LOGITS
    (dict
    0.07
    _dec
    0.07
    notated
    0.07
     track
    0.07
    _context
    0.06
    rose
    0.06
    比べ
    0.06
    ’.
    0.06
    cth
    0.06
     crossing
    0.06
    Activations Density 0.056%

    No Known Activations