© 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. 5854
    Prev
    Next
    INDEX
    Explanations

    code

    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
    ç½ijæł¼
    -0.30
    çķĻç»Ļ
    -0.28
    eland
    -0.25
    jal
    -0.25
    è¿ĩ
    -0.25
     sulph
    -0.24
    éĢļè¡Įè¯ģ
    -0.24
    è¿ĩ大
    -0.24
     Planner
    -0.23
     Paz
    -0.23
    POSITIVE LOGITS
    iano
    0.27
    anship
    0.24
    åľ¨æķ´ä¸ª
    0.24
    æĬļ
    0.24
     neu
    0.23
     gir
    0.23
    éĺŁä¼į
    0.23
    ÑĪÑĥ
    0.23
     breakout
    0.23
    AMA
    0.23
    Activations Density 0.400%

    No Known Activations