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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 162753
    Prev
    Next
    INDEX
    Explanations

    support, technical documentation

    np_max-act · gemini-2.0-flash
    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
    å®Įåħ¨
    -0.29
    é½IJ
    -0.29
     completely
    -0.28
    åŁºæľ¬ä¿¡æģ¯
    -0.28
    çļĦåŁºæľ¬
    -0.28
    çļĦä¸Ģ大
    -0.28
     synchronized
    -0.27
    yme
    -0.26
     immediate
    -0.26
    åIJijä¸Ĭ
    -0.26
    POSITIVE LOGITS
     other
    0.78
    åħ¶ä»ĸ
    0.70
    other
    0.65
    åħ¶ä»ĸçļĦ
    0.65
    Other
    0.64
    åħ¶ä»ĸåĽ½å®¶
    0.64
     Other
    0.63
    åħ¶å®ĥ
    0.63
    _other
    0.58
    åĪ«çļĦ
    0.57
    Activations Density 0.002%

    No Known Activations