© 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. 162374
    Prev
    Next
    INDEX
    Explanations

    are

    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
     planners
    -0.29
    psilon
    -0.29
    å¯Ĩ
    -0.27
    èĦ¸
    -0.27
    å¸ĥ
    -0.26
    ç¬ij
    -0.26
    raph
    -0.26
    yles
    -0.26
    plan
    -0.25
    MAP
    -0.25
    POSITIVE LOGITS
    å½¢å¼ı
    0.35
    olson
    0.32
    çļĦå½¢å¼ı
    0.28
     FORM
    0.28
     form
    0.28
    æ¹¾åĮº
    0.27
     forme
    0.27
    ))^
    0.27
    _form
    0.27
     nomine
    0.27
    Activations Density 0.019%

    No Known Activations