© 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. 107288
    Prev
    Next
    INDEX
    Explanations

    finding solutions

    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
    æľĿ
    -0.29
    aran
    -0.27
     [][]
    -0.26
    å¼ĵ
    -0.26
    ŀĭ
    -0.25
    =en
    -0.25
    .series
    -0.25
    æľĢéļ¾
    -0.24
    ä¸ŃéĹ´
    -0.24
    _cast
    -0.24
    POSITIVE LOGITS
     fils
    0.27
    lements
    0.27
    æĪijæīį
    0.26
    æīį
    0.26
     circum
    0.26
    ä¸Ĭå¹´åIJĮæľŁ
    0.25
     cul
    0.25
    eof
    0.25
    zia
    0.25
    æīįåı¯ä»¥
    0.25
    Activations Density 17.496%

    No Known Activations