© 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. 5939
    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
    è§ģè¯ģ
    -0.29
    otec
    -0.28
    TRACK
    -0.27
    æĹ¥å¤ľ
    -0.26
     Bam
    -0.26
    ToFit
    -0.26
     Lac
    -0.26
    favorites
    -0.25
    ovi
    -0.25
    ä¸ªå·¥ä½ľæĹ¥
    -0.24
    POSITIVE LOGITS
    ats
    0.31
    ving
    0.25
    羣æŃ£çļĦ
    0.25
     permanent
    0.24
    sp
    0.24
    -than
    0.24
     diagram
    0.24
     kiá»ĩm
    0.24
    ä»»ä½ķ人
    0.24
    way
    0.24
    Activations Density 0.028%

    No Known Activations

    This feature has no known activations.