© 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. 5206
    Prev
    Next
    INDEX
    Explanations

    condition, exchange, requirement

    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
     Civilization
    -0.28
     Commerce
    -0.25
    CENT
    -0.25
    åĬ³åĬ¨åIJĪåIJĮ
    -0.25
     zm
    -0.25
    (am
    -0.25
    çŁ³å¤´
    -0.24
    atable
    -0.24
    éļı
    -0.24
    对ä»ĺ
    -0.23
    POSITIVE LOGITS
    oso
    0.28
     PROGMEM
    0.28
    ãģĭãģijãģ¦
    0.27
     Wr
    0.26
     mapping
    0.26
    rics
    0.26
     shadows
    0.26
    icorn
    0.25
    -reviewed
    0.25
    nas
    0.25
    Activations Density 0.003%

    No Known Activations