© 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. 5830
    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
    åĩij
    -0.27
    inois
    -0.27
     theory
    -0.26
    å§Ķç»Ħç»ĩ
    -0.25
    æµ®
    -0.25
    igo
    -0.24
     He
    -0.24
    hte
    -0.24
    clipse
    -0.23
    è®ĵä»ĸ
    -0.23
    POSITIVE LOGITS
     skins
    0.28
    éĤ¦
    0.27
    æĬ¤
    0.26
     recl
    0.25
    æīĭ
    0.25
    /host
    0.24
    (TM
    0.24
     hookup
    0.24
    ividad
    0.24
    itan
    0.24
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.