© 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. 64373
    Prev
    Next
    INDEX
    Explanations

    science and 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
    abet
    -0.29
    ox
    -0.25
    esto
    -0.25
    lei
    -0.25
    渥
    -0.25
    /inc
    -0.25
     Fet
    -0.24
    Ont
    -0.23
    izzare
    -0.23
     аб
    -0.23
    POSITIVE LOGITS
    çļĦæľĢåIJİä¸Ģ
    0.30
    trä
    0.28
     cann
    0.28
    ç¥Ń
    0.28
    è¿Ļ对äºİ
    0.26
    aling
    0.26
    æĿ
    0.25
    åĺĢ
    0.25
     occasion
    0.24
    被è§Ĩ为
    0.24
    Activations Density 90.012%

    No Known Activations