© 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. 5704
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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¸ĢæĬĬ
    -0.33
    orama
    -0.27
    /latest
    -0.26
    entine
    -0.25
    REW
    -0.25
    ä¸Ģå¤ľ
    -0.24
     projections
    -0.24
    wares
    -0.24
     Projection
    -0.24
    OMEM
    -0.24
    POSITIVE LOGITS
     survivor
    0.30
     Survival
    0.30
    æĻ¶ä½ĵ
    0.27
     survive
    0.27
     survival
    0.26
     Sellers
    0.26
    Bug
    0.26
     yếu
    0.25
     survived
    0.25
    urv
    0.25
    Activations Density 0.047%

    No Known Activations

    This feature has no known activations.