© 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. 163441
    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
    泡
    -0.29
    _XDECREF
    -0.29
    SSIP
    -0.26
     policy
    -0.26
    éļĹ
    -0.25
    odo
    -0.25
     sharing
    -0.25
    åĶ®åįĸ
    -0.25
    _odd
    -0.24
    mdb
    -0.24
    POSITIVE LOGITS
    æľī害
    0.26
    åħ¨èĥ½
    0.24
     reap
    0.24
    让人们
    0.24
    è¡Ģ液
    0.24
    åĪĽéĢłæĢ§
    0.24
    人ä½ĵ
    0.24
    çľŁäºº
    0.24
    åħ¨æĻ¯
    0.24
    .getLog
    0.24
    Activations Density 0.022%

    No Known Activations

    This feature has no known activations.