© 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. 163362
    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
    utar
    -0.25
    -car
    -0.23
     synt
    -0.23
    æįŁ
    -0.22
     Ra
    -0.22
    /car
    -0.22
    ry
    -0.22
    ä¸ĢåĪĩ
    -0.21
    .car
    -0.21
    ÃŃ
    -0.21
    POSITIVE LOGITS
    éŃħ
    0.25
    mland
    0.24
    ĽĦ
    0.24
    ︶
    0.23
    subjects
    0.22
    åħ¬åħ±èµĦæºIJ
    0.22
    alley
    0.22
     subjects
    0.22
     Lomb
    0.21
    _km
    0.21
    Activations Density 0.008%

    No Known Activations

    This feature has no known activations.