© 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. 107734
    Prev
    Next
    INDEX
    Explanations

    the

    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
    马
    -0.28
    èĮ´
    -0.27
    _PP
    -0.25
     Er
    -0.24
     scr
    -0.24
    /licenses
    -0.24
    认
    -0.24
    åĪģ
    -0.24
    rire
    -0.24
    产ä¸ļéĽĨèģļ
    -0.24
    POSITIVE LOGITS
    utt
    0.30
    efined
    0.27
    uned
    0.25
    /moment
    0.25
     Subjects
    0.25
    alte
    0.24
    YTE
    0.24
     cor
    0.24
    èĢģ人家
    0.24
    -corner
    0.24
    Activations Density 5.998%

    No Known Activations