© 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. 5285
    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
    iverse
    -0.28
    æ»ļåĬ¨
    -0.27
    yte
    -0.26
    æ¾¹
    -0.26
    æĮ¡
    -0.25
    /cache
    -0.24
    osphere
    -0.23
    ingly
    -0.23
    éĩįçĶŁ
    -0.23
    cing
    -0.23
    POSITIVE LOGITS
    åĬłæĭ¿
    0.28
    åĵģ
    0.28
    stadt
    0.25
    æŃ£å®Ĺ
    0.25
     enquiries
    0.25
    åĵģè´¨
    0.24
    åľºåIJĪ
    0.24
     Choices
    0.24
    pees
    0.23
    preg
    0.23
    Activations Density 0.145%

    No Known Activations

    This feature has no known activations.