© 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. 5722
    Prev
    Next
    INDEX
    Explanations

    commas

    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
    appointment
    -0.26
    paren
    -0.25
    angled
    -0.24
     THESE
    -0.24
     rhetorical
    -0.24
    prene
    -0.24
    èĶĮ
    -0.23
    ãģĵãĤĮãĤī
    -0.23
    è¿ĻäºĽ
    -0.23
    dra
    -0.23
    POSITIVE LOGITS
    èģĬ
    0.29
    ä¼ı
    0.27
    amat
    0.26
    anian
    0.25
    äºĴè¡¥
    0.25
    ãģĹãģ¦ãĤĤ
    0.25
    edio
    0.25
    x
    0.24
    ins
    0.24
    èİ«åIJį
    0.24
    Activations Density 0.006%

    No Known Activations