© 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. 19-TRANSCODER-HP
    7. 5956
    Prev
    Next
    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸ĬçļĦ
    -0.29
    设计æĸ¹æ¡Ī
    -0.29
    wel
    -0.27
    edly
    -0.27
    lates
    -0.27
    æł¸å®ļ
    -0.26
    æĢģ
    -0.25
    -side
    -0.25
    ä¹Łä¸º
    -0.25
    .ng
    -0.24
    POSITIVE LOGITS
     parach
    0.27
     lum
    0.26
    ksen
    0.26
    orum
    0.26
    pages
    0.25
    uries
    0.25
    parallel
    0.24
    ularity
    0.24
    osaic
    0.24
    ãĤŃãĥ³ãĤ°
    0.24
    Activations Density 0.023%

    No Known Activations