© 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. 162497
    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
     subparagraph
    -0.26
    abaj
    -0.26
     earners
    -0.26
     Neuroscience
    -0.26
    iges
    -0.24
    侪
    -0.24
    .Contracts
    -0.24
    ybrid
    -0.24
     thirds
    -0.23
    妾
    -0.23
    POSITIVE LOGITS
    éĵ³
    0.30
     allowable
    0.28
    ENE
    0.25
    足迹
    0.25
    åŁĥ
    0.24
    å¸ĪçĶŁ
    0.24
    èµĽåIJİ
    0.24
     leader
    0.24
     VIC
    0.23
    误差
    0.23
    Activations Density 0.021%

    No Known Activations

    This feature has no known activations.