© 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. 162412
    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
     obsÅĤ
    -0.30
     initialised
    -0.28
     paramName
    -0.25
    æįŁåĿı
    -0.25
     scrapped
    -0.24
     programmes
    -0.24
    妨ç¢į
    -0.24
    oping
    -0.24
     troch
    -0.23
    tc
    -0.23
    POSITIVE LOGITS
     اÙĦÙħÙĤ
    0.29
    'label
    0.28
    -label
    0.27
    onaut
    0.26
    uity
    0.26
    boat
    0.26
    çķĻä¸ĭæĿ¥
    0.25
    ship
    0.25
    ipel
    0.25
    .Label
    0.25
    Activations Density 0.136%

    No Known Activations

    This feature has no known activations.