© 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. 108075
    Prev
    Next
    INDEX
    Explanations

    Instructions and documentation

    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
    upos
    -0.29
    Which
    -0.28
     Whats
    -0.26
     amplitude
    -0.26
     Which
    -0.26
    ä½łèĩªå·±
    -0.26
     dial
    -0.25
    indows
    -0.25
    ANT
    -0.24
    èĢĮçİ°åľ¨
    -0.24
    POSITIVE LOGITS
     Generation
    0.29
     Schul
    0.26
    ired
    0.25
    èĭ¦
    0.25
     sch
    0.25
    STALL
    0.25
    åİ
    0.24
    对åѦçĶŁ
    0.24
     scp
    0.24
     sal
    0.24
    Activations Density 14.452%

    No Known Activations