© 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. 64282
    Prev
    Next
    INDEX
    Explanations

    is

    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
    ä¹ħäºĨ
    -0.28
    èµĺ
    -0.27
    æľīæľŁ
    -0.26
    è®¤çŁ¥
    -0.25
    æĦŁäºº
    -0.25
    NAMESPACE
    -0.25
     Crafts
    -0.24
    æĿ¿æĿIJ
    -0.24
    Criteria
    -0.23
    ysts
    -0.23
    POSITIVE LOGITS
    ç®ķ
    0.28
    åħĭ
    0.27
    èį¨
    0.26
     hope
    0.26
     Duch
    0.26
     pois
    0.26
    æį¢æĪIJ
    0.25
    merged
    0.25
    rone
    0.25
    ä¸Ģåı¥
    0.25
    Activations Density 17.363%

    No Known Activations