© 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. 162346
    Prev
    Next
    INDEX
    Explanations

    age

    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
    s
    -0.38
    said
    -0.33
    sse
    -0.32
    says
    -0.30
    sut
    -0.29
    sar
    -0.29
    sites
    -0.29
    sburg
    -0.28
    sic
    -0.28
    sus
    -0.28
    POSITIVE LOGITS
    less
    0.37
     of
    0.32
    ing
    0.31
    ored
    0.28
    in
    0.28
    lessness
    0.28
    c
    0.28
    Of
    0.27
    of
    0.27
    a
    0.26
    Activations Density 0.093%

    No Known Activations