© 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. 63601
    Prev
    Next
    INDEX
    Explanations

    survey/study

    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
    åįĥ
    -0.29
    ä¸īç»´
    -0.26
    -Ta
    -0.26
     Affero
    -0.26
    vars
    -0.26
     laisse
    -0.25
    éra
    -0.24
    xde
    -0.24
    éĻ¤åİ»
    -0.24
    å¾ĹåĪĨ
    -0.23
    POSITIVE LOGITS
     Prompt
    0.26
    è¿Ļæĺ¯æĪij们
    0.25
    held
    0.25
    -cond
    0.25
     cond
    0.25
     prer
    0.25
    æĹ¥äº§
    0.24
    ãĥŀãĥ«
    0.24
    elage
    0.24
    åŀŃ
    0.24
    Activations Density 1.696%

    No Known Activations