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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 88463
    Prev
    Next
    INDEX
    Explanations

    computing and data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onis
    -0.26
    erview
    -0.26
    ugen
    -0.26
    azzi
    -0.26
    GENER
    -0.26
    rell
    -0.25
    rieg
    -0.25
    为äºĨ让
    -0.24
    erton
    -0.24
     presume
    -0.24
    POSITIVE LOGITS
    Different
    0.34
     Different
    0.30
    APH
    0.30
    different
    0.30
     different
    0.27
    ä¸įåIJĮçļĦ
    0.27
    _different
    0.27
    å®Įåħ¨ä¸įåIJĮ
    0.26
     oli
    0.26
    æį¢æĿ¥
    0.26
    Activations Density 0.015%

    No Known Activations