© 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. 107108
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
     hint
    -0.27
    o
    -0.25
    约
    -0.24
     waste
    -0.24
    °F
    -0.24
    åĽļ
    -0.24
    .ndim
    -0.23
     Ñģебе
    -0.23
    å¤ļç§į
    -0.23
    éĴĵ
    -0.23
    POSITIVE LOGITS
    ä½Ĩæĺ¯å¦Ĥæŀľ
    0.30
    igner
    0.29
    ä½Ĩæĺ¯ä»ĸ
    0.28
    atorial
    0.27
     CreateUser
    0.26
    ToolStrip
    0.26
    éĽĨåĽ¢èĤ¡ä»½
    0.26
    orizontal
    0.25
    (er
    0.25
    irectional
    0.25
    Activations Density 26.019%

    No Known Activations