© 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. 163828
    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
     vä
    -0.26
    ittal
    -0.25
    éªIJ
    -0.25
    å¼ĭ
    -0.25
    osaur
    -0.25
     prio
    -0.24
    èĪĽ
    -0.24
    èĬĪ
    -0.24
    ewis
    -0.24
     vuel
    -0.24
    POSITIVE LOGITS
     Sand
    0.36
     sand
    0.32
     green
    0.30
    con
    0.29
    Sand
    0.27
    unta
    0.27
    sand
    0.27
    green
    0.27
    sign
    0.26
    绿
    0.26
    Activations Density 0.012%

    No Known Activations

    This feature has no known activations.