© 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. 97812
    Prev
    Next
    INDEX
    Explanations

    Code and math

    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
    æľ¬æ¡Ī
    -0.29
    è¿Ļä¸Ģ次
    -0.27
     Vaugh
    -0.26
     CGContext
    -0.26
     Ingram
    -0.26
    /fa
    -0.25
    æī¶
    -0.25
    roc
    -0.25
     Vad
    -0.24
    åľ¨è¿Ļæĸ¹éĿ¢
    -0.23
    POSITIVE LOGITS
    izzo
    0.28
    ez
    0.25
    çľĭä½ł
    0.25
    addle
    0.24
    omez
    0.24
    ector
    0.24
    elight
    0.24
    åİŁåŀĭ
    0.24
    andez
    0.24
    åħ¨æ°ij
    0.23
    Activations Density 0.003%

    No Known Activations