© 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. 5450
    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
     sprintf
    -0.29
    ickness
    -0.28
     prol
    -0.26
    мÑı
    -0.25
    ifax
    -0.25
    å·¦æīĭ
    -0.25
    	sprintf
    -0.25
    ($)
    -0.24
    -ser
    -0.24
    ickers
    -0.24
    POSITIVE LOGITS
    riendly
    0.27
    çĤĴ
    0.26
    æĿ¥ä¸įåıĬ
    0.25
    uled
    0.24
    ularity
    0.24
    æĿĥéĻIJ
    0.24
    æĭĽ
    0.24
     Tar
    0.24
    ENABLE
    0.24
    chts
    0.23
    Activations Density 0.010%

    No Known Activations

    This feature has no known activations.