© 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. 63332
    Prev
    Next
    INDEX
    Explanations

    Sentence beginnings

    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
    è¿Ļ两ç§į
    -0.32
    æľĶ
    -0.28
    è¿ĺæľīä»Ģä¹Ī
    -0.27
    ;&#
    -0.26
    åīįèĢħ
    -0.26
    äºĮèĢħ
    -0.26
    两èĢħ
    -0.25
    è¿Ļæĺ¯æĪij们
    -0.25
    yes
    -0.24
    s
    -0.24
    POSITIVE LOGITS
    wick
    0.28
    berger
    0.26
    .LE
    0.26
    wagon
    0.26
    aign
    0.26
    LETE
    0.25
    .Inv
    0.25
    åľĪåŃIJ
    0.25
    uell
    0.25
    _invoke
    0.25
    Activations Density 34.885%

    No Known Activations