© 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. 5848
    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
     objection
    -0.26
    æĸ°ç¯ĩç«ł
    -0.26
    ombre
    -0.26
    çķĻå®Ī
    -0.25
     gladly
    -0.24
    -setting
    -0.24
     ass
    -0.23
    äºļè¿IJ
    -0.23
    表æĢģ
    -0.23
    elcome
    -0.23
    POSITIVE LOGITS
    &o
    0.28
    å©
    0.28
    èķ´
    0.26
    abal
    0.26
    burn
    0.24
    æľ¬èº«
    0.24
    аÑĤоÑĢ
    0.24
    оÑĤоÑĢ
    0.24
    TypeID
    0.24
    å°ĸ
    0.24
    Activations Density 0.915%

    No Known Activations

    This feature has no known activations.