© 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. 22-TRANSCODER-HP
    7. 130440
    Prev
    Next
    INDEX
    Explanations

    Technical and legal documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     internally
    -0.32
     pragma
    -0.31
    对å¤ĸ
    -0.30
     externally
    -0.29
    å¤ĸéĥ¨
    -0.29
    å®ŀéĻħ
    -0.28
    çļĦå®ŀéĻħ
    -0.28
     practical
    -0.28
     external
    -0.28
    æĹ¥å¸¸çĶŁæ´»
    -0.28
    POSITIVE LOGITS
    ä¸Ģçĵ¶
    0.27
    æ¦Ķ
    0.26
     اÙĦعÙĨ
    0.26
    lim
    0.25
    åIJĮæł·æĺ¯
    0.25
     æĽ
    0.25
    ant
    0.25
    åįģåŃĹ
    0.25
    onym
    0.25
    åĵģç±»
    0.24
    Activations Density 0.007%

    No Known Activations