© 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. 107212
    Prev
    Next
    INDEX
    Explanations

    questions about 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
    士
    -0.26
    atically
    -0.25
    pto
    -0.25
    鸥
    -0.25
    imately
    -0.24
    RelativeTo
    -0.24
     götür
    -0.24
    ToShow
    -0.24
    ä¾Ŀçħ§
    -0.23
    ATIC
    -0.23
    POSITIVE LOGITS
     mix
    0.29
    åĩ¡äºĭ
    0.26
    nak
    0.26
    mund
    0.26
    bigint
    0.26
    æ··åIJĪ
    0.26
    план
    0.25
     grandson
    0.25
     cita
    0.25
     mixture
    0.25
    Activations Density 0.900%

    No Known Activations