© 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. 162373
    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
     Tune
    -0.29
     Stones
    -0.29
    Bang
    -0.28
     Disc
    -0.28
     Separator
    -0.26
    ä¸įçIJĨ
    -0.26
     Incident
    -0.26
     Campaign
    -0.25
     Tos
    -0.25
    ffe
    -0.25
    POSITIVE LOGITS
     rep
    0.32
     men
    0.29
    loom
    0.28
     pet
    0.27
     report
    0.27
     intra
    0.26
    odia
    0.26
    顼
    0.26
    ij
    0.26
     protocol
    0.25
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.