© 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. 141773
    Prev
    Next
    INDEX
    Explanations

    ubes

    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
    èIJ½åľ¨
    -0.27
    agh
    -0.26
     '),
    -0.26
    leon
    -0.25
    /Internal
    -0.24
    éĢģç»Ļ
    -0.24
     Äijá»Ŀi
    -0.24
     Kills
    -0.24
    ublic
    -0.24
    ALA
    -0.24
    POSITIVE LOGITS
    foot
    0.28
    足
    0.27
    icated
    0.25
    å§Ķ
    0.25
    perse
    0.25
    åµĭ
    0.25
    ãģ¨ãģĨ
    0.25
     matters
    0.24
    DOCTYPE
    0.24
    ven
    0.24
    Activations Density 16.528%

    No Known Activations