© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 162363
    Prev
    Next
    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åIJijçĿĢ
    -0.31
     addCriterion
    -0.26
    eating
    -0.26
    è¾Ł
    -0.26
    posing
    -0.26
    ä¸ĭçıŃ
    -0.26
    ertools
    -0.25
     feeding
    -0.25
     confidential
    -0.24
    itical
    -0.24
    POSITIVE LOGITS
    æł¡éķ¿
    0.28
    å±ī
    0.27
     Stress
    0.27
     representatives
    0.27
    vice
    0.26
    代表
    0.26
    .breakpoints
    0.25
    ONSE
    0.25
    è´Łè´£äºº
    0.25
    ãĤµãĥ¼
    0.24
    Activations Density 0.008%

    No Known Activations