© 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. 5176
    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
    ves
    -0.31
     consistently
    -0.30
    åį°
    -0.30
    äºĽ
    -0.29
    ache
    -0.29
    æŀ¯
    -0.29
    awy
    -0.28
     up
    -0.27
     brow
    -0.26
    ç°ĩ
    -0.26
    POSITIVE LOGITS
    ifix
    0.28
    fadeOut
    0.27
    adera
    0.27
     lia
    0.27
    交æµģåIJĪä½ľ
    0.26
    rang
    0.25
    enÃŃ
    0.25
     اÙĦعاص
    0.25
    chang
    0.25
    DEST
    0.24
    Activations Density 1.880%

    No Known Activations

    This feature has no known activations.