© 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. 20-TRANSCODER-HP
    7. 63909
    Prev
    Next
    INDEX
    Explanations

    body mass

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä»»ä½ķæŶåĢĻ
    -0.26
    ipheral
    -0.25
    ä¸ĵä¸ļæĬĢæľ¯
    -0.25
    æĺ¥ç§ĭ
    -0.24
     parties
    -0.24
    วย
    -0.24
    -0.23
    _regular
    -0.23
    ADR
    -0.23
    å½ĵäºĭ
    -0.23
    POSITIVE LOGITS
    zem
    0.25
     refining
    0.25
     OPTIONS
    0.25
    å¿ĥæĢģ
    0.24
    æĮº
    0.23
    Ī
    0.23
     zak
    0.23
    ÇĶ
    0.23
     Tops
    0.23
    èѦæĥķ
    0.23
    Activations Density 8.198%

    No Known Activations