© 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. 5297
    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
     reuse
    -0.32
     reused
    -0.27
     comparison
    -0.26
    -groups
    -0.25
     deriv
    -0.25
    piar
    -0.24
     Ames
    -0.24
     games
    -0.24
     Relationship
    -0.24
    uilt
    -0.24
    POSITIVE LOGITS
    ìĤ¬ëĬĶ
    0.28
    éŸ
    0.27
    inst
    0.27
    ano
    0.26
    sgi
    0.26
    tsy
    0.26
    pow
    0.25
    æīĺ
    0.25
    invisible
    0.25
    æ´ĭ
    0.25
    Activations Density 0.115%

    No Known Activations

    This feature has no known activations.