© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 24288
    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
    鸣
    -0.26
    ctal
    -0.26
    ä¸ĢåľĪ
    -0.25
    adoo
    -0.23
     lots
    -0.23
    ä¼½
    -0.23
    å²©çŁ³
    -0.23
    åľĪ
    -0.23
    é¢IJ
    -0.23
    人们çļĦ
    -0.23
    POSITIVE LOGITS
    夫人
    0.25
     полов
    0.25
    ¯
    0.24
    俸
    0.24
    樣
    0.23
    croft
    0.23
    æł·çļĦ
    0.23
     refund
    0.23
    éĺ¿å§¨
    0.23
     directly
    0.22
    Activations Density 0.152%

    No Known Activations

    This feature has no known activations.