© 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. 87936
    Prev
    Next
    INDEX
    Explanations

    collaboration and working together

    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
     dors
    -0.26
    Defense
    -0.24
     Dominion
    -0.24
     domin
    -0.24
    éĥ¨éŨ
    -0.24
     admin
    -0.24
     offenses
    -0.23
    admin
    -0.23
    dom
    -0.23
     domestic
    -0.23
    POSITIVE LOGITS
    ä¸įæĸŃ
    0.33
    ä¸įæĸŃçļĦ
    0.32
    ä¸įæĸŃåľ°
    0.28
    lopen
    0.27
    ä¸įåģľçļĦ
    0.27
     constantly
    0.26
    undry
    0.26
    äºĴè¡¥
    0.26
    æºIJæºIJ
    0.26
    é¼ĵåĬ±
    0.25
    Activations Density 0.008%

    No Known Activations