© 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. 107632
    Prev
    Next
    INDEX
    Explanations

    Code and packages

    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
    chia
    -0.25
     chiropr
    -0.25
    filer
    -0.25
    æĶ¶åĪ°äºĨ
    -0.25
     ÑĢавно
    -0.25
    .Rem
    -0.25
    .shtml
    -0.25
    ÅĤoÅĽÄĩ
    -0.24
    CRET
    -0.24
    keley
    -0.24
    POSITIVE LOGITS
    [*
    0.29
    MP
    0.28
     over
    0.27
     environment
    0.27
     environmental
    0.27
     necess
    0.27
    [\
    0.25
     Napoli
    0.25
     hot
    0.25
    thin
    0.25
    Activations Density 0.390%

    No Known Activations