© 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. 162637
    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_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
    èĢĮä¸Ķ
    -0.29
    ä¸Ķ
    -0.28
    临
    -0.27
    abl
    -0.27
     Morr
    -0.26
    cho
    -0.26
    *
    -0.26
    .locale
    -0.25
    è®´
    -0.25
    ...(
    -0.25
    POSITIVE LOGITS
    .twig
    0.28
    â¼¼
    0.27
    ynos
    0.27
    اÙĨÙĬا
    0.26
     sharp
    0.26
     clear
    0.25
    ptune
    0.25
    amic
    0.24
    elsen
    0.24
    WAYS
    0.24
    Activations Density 0.002%

    No Known Activations