© 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. 23-TRANSCODER-HP
    7. 162288
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     half
    -0.29
     narrowly
    -0.27
    orian
    -0.26
    ILog
    -0.26
    .iter
    -0.26
    尾巴
    -0.25
    least
    -0.25
    å°ĸ
    -0.25
    å¹¼
    -0.25
     Plum
    -0.25
    POSITIVE LOGITS
    @Module
    0.31
     summoned
    0.28
    urb
    0.27
    AGEMENT
    0.26
    åħ¥é©»
    0.25
    æľīèī²éĩijå±ŀ
    0.25
    /desktop
    0.25
    æģĥ
    0.24
    hausen
    0.24
    moduleId
    0.24
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.