© 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. 162349
    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
    æŃĨ
    -0.28
    æĪİ
    -0.26
     Emerson
    -0.25
     cen
    -0.25
     Ease
    -0.24
     Amen
    -0.24
    _SLOT
    -0.24
    绪
    -0.23
    .EventQueue
    -0.23
    Slot
    -0.23
    POSITIVE LOGITS
    anean
    0.28
    enschaft
    0.28
    ftware
    0.27
    istik
    0.26
    IBUT
    0.25
    ç»ĵæĻ¶
    0.25
    antry
    0.25
    acle
    0.25
    lichkeit
    0.25
    Crystal
    0.25
    Activations Density 0.003%

    No Known Activations

    This feature has no known activations.