© 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. 5767
    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
    ta
    -0.31
     именно
    -0.29
    ja
    -0.28
    æĺİæĹ¥
    -0.27
    ÑĤ
    -0.25
     mere
    -0.25
     Wilde
    -0.25
    ä¸ĢæĹ¥
    -0.24
     Val
    -0.24
    osing
    -0.24
    POSITIVE LOGITS
    èĢĮä¸į
    0.29
    adar
    0.28
    æłı
    0.25
     neighb
    0.24
    大大
    0.24
    emes
    0.23
     IPP
    0.23
    abar
    0.23
    áºłI
    0.23
     Cary
    0.23
    Activations Density 0.031%

    No Known Activations

    This feature has no known activations.