© 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. 107512
    Prev
    Next
    INDEX
    Explanations

    Technical documentation

    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
    ilda
    -0.30
    åij¨
    -0.29
    zier
    -0.26
    ifer
    -0.26
    ASN
    -0.25
    ÑĤелÑĮ
    -0.25
    toInt
    -0.25
    CHO
    -0.25
     toxin
    -0.25
    票
    -0.25
    POSITIVE LOGITS
    adol
    0.31
    ä¹IJè§Ĥ
    0.29
    олов
    0.29
    oku
    0.27
     concl
    0.27
    Conclusion
    0.26
     Ment
    0.26
    ç»ıèIJ¥
    0.25
    ÙħÙĨت
    0.25
     planes
    0.24
    Activations Density 3.623%

    No Known Activations