© 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. 162319
    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
    inati
    -0.31
    çı©
    -0.31
    Ã¼ÃŁ
    -0.30
    çīĮçħ§
    -0.27
    ä½İä½į
    -0.26
    å·į
    -0.25
    orgh
    -0.25
    åıĭ好
    -0.25
    tz
    -0.24
     blush
    -0.24
    POSITIVE LOGITS
    batim
    0.28
     Slug
    0.28
     Am
    0.26
     Spread
    0.26
    Am
    0.26
     slug
    0.26
     sl
    0.25
    :
    0.25
    Spread
    0.25
     Sl
    0.25
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.