© 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. 5864
    Prev
    Next
    INDEX
    Explanations

    digits

    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
    æĸ°æ¨¡å¼ı
    -0.28
    etz
    -0.27
    uper
    -0.26
    广
    -0.25
    æĢ»ä½ĵ
    -0.25
    edral
    -0.25
    游
    -0.24
    æĸ°
    -0.24
     resume
    -0.24
     banned
    -0.24
    POSITIVE LOGITS
    ä¹Łä¸įä¾ĭå¤ĸ
    0.28
     Lever
    0.28
    scriptId
    0.27
    lider
    0.25
     mojo
    0.24
    è·ijåİ»
    0.24
     lesser
    0.24
    ä½Ĩæĺ¯å¯¹äºİ
    0.24
    CBC
    0.24
    ICODE
    0.24
    Activations Density 0.012%

    No Known Activations