© 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. 63625
    Prev
    Next
    INDEX
    Explanations

    Code/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
    麽
    -0.29
    麼
    -0.26
    è¿ĺä¸įæĺ¯
    -0.26
    dek
    -0.25
    ä¿®
    -0.25
    çľĭä¸įè§ģ
    -0.25
    ongan
    -0.25
     Dak
    -0.25
    èĢĮéĿŀ
    -0.25
    å¾ĹåĪ°æľīæķĪ
    -0.24
    POSITIVE LOGITS
    fc
    0.27
    .ot
    0.26
    åĥŃ
    0.25
    uestion
    0.24
     reflect
    0.24
     Bürger
    0.24
    Alan
    0.23
    èĭĹ
    0.23
     glm
    0.23
    Ãło
    0.23
    Activations Density 20.883%

    No Known Activations