© 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. 141493
    Prev
    Next
    INDEX
    Explanations

    Adjectives

    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
    éŨå¤ĸ
    -0.30
    _stack
    -0.26
     bible
    -0.26
    ä¸į足以
    -0.26
     Sidney
    -0.26
     sur
    -0.26
    æ°¸è¿ľä¸įä¼ļ
    -0.26
    виз
    -0.25
    Stack
    -0.25
    ames
    -0.25
    POSITIVE LOGITS
    åĽ¢åijĺ
    0.28
    heed
    0.27
    ä¸ĢåĽ¢
    0.27
    åĽ¢éķ¿
    0.27
    tör
    0.25
    hoc
    0.25
     Huck
    0.24
     bach
    0.24
     Boolean
    0.24
    tor
    0.24
    Activations Density 11.135%

    No Known Activations