© 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. 142305
    Prev
    Next
    INDEX
    Explanations

    Technical discussions or programming

    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
     gauge
    -0.28
    äºĭçī©
    -0.27
    kowski
    -0.27
     community
    -0.26
     life
    -0.26
    æł¡
    -0.26
     cor
    -0.25
     reading
    -0.25
    ÃŃ
    -0.25
    ral
    -0.25
    POSITIVE LOGITS
    edin
    0.27
    opper
    0.27
    "...
    0.26
     ~>
    0.26
    éĢļè¡Į
    0.24
    讼
    0.24
     Hwy
    0.24
    å©Ĩå©Ĩ
    0.24
     spons
    0.24
    _skip
    0.24
    Activations Density 9.745%

    No Known Activations