© 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. 88383
    Prev
    Next
    INDEX
    Explanations

    Documentation/Code/Writing

    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
    çļ±çº¹
    -0.27
     Jeb
    -0.25
    åį¡è½¦
    -0.25
    æĿ¥æºIJäºİ
    -0.24
    łģ
    -0.24
     second
    -0.24
    第äºĮ
    -0.24
    éĢģ
    -0.23
     اÙĦثاÙĨÙĬØ©
    -0.23
     wrapped
    -0.23
    POSITIVE LOGITS
    è¿ĻäºĽä¸ľè¥¿
    0.38
    缸åħ³ä¿¡æģ¯
    0.29
    è¿ĻäºĽéĹ®é¢ĺ
    0.29
     demographics
    0.28
    ographics
    0.27
     goodies
    0.27
    éģĤ
    0.27
    ivor
    0.27
    ivities
    0.27
     scenarios
    0.25
    Activations Density 0.001%

    No Known Activations