© 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. 18-TRANSCODER-HP
    7. 89179
    Prev
    Next
    INDEX
    Explanations

    hands and fingers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rapped
    -0.26
     Asked
    -0.25
    ADVERTISEMENT
    -0.25
    &amp
    -0.25
    æ¨¡æł·
    -0.25
    uesta
    -0.24
    OperationException
    -0.24
    <bool
    -0.24
    č↵        č↵
    -0.23
    èģļ
    -0.23
    POSITIVE LOGITS
     genu
    0.27
     stor
    0.26
     hum
    0.26
     lut
    0.26
    éĺ»æŃ¢
    0.25
     mechanisms
    0.24
    忸
    0.24
    åij¶
    0.24
    ç¥ŀéĢļ
    0.24
    çIJ¶
    0.24
    Activations Density 21.347%

    No Known Activations