© 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. 19-TRANSCODER-HP
    7. 8871
    Prev
    Next
    INDEX
    Explanations

    Scientific/legal publications and abbreviations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĨįå¤ļ
    -0.28
    .getAmount
    -0.28
    ecycle
    -0.26
    )/
    -0.25
    å¹ķ
    -0.25
    .bd
    -0.25
    ona
    -0.25
    æĹ¥æŃ£å¼ı
    -0.25
    纳æĸ¯
    -0.25
    度
    -0.25
    POSITIVE LOGITS
    说èĩªå·±
    0.29
    erner
    0.28
    abor
    0.27
    adiator
    0.27
    obby
    0.26
    ollo
    0.25
     Moff
    0.24
    pto
    0.24
    Canonical
    0.24
    ýt
    0.23
    Activations Density 0.014%

    No Known Activations