© 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. 87592
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    è¿Ļç§įæĸ¹å¼ı
    -0.31
    æ··
    -0.29
    åľ¨æѤ
    -0.28
    á»ijn
    -0.27
    æŀģ
    -0.26
    åľ¨è¿Ļç§į
    -0.26
    å¤įæĿĤ
    -0.26
    Sorted
    -0.26
     They
    -0.25
    ä»ĸ们éĥ½
    -0.25
    POSITIVE LOGITS
    /arch
    0.27
    itere
    0.26
    æĺ¯æĪij
    0.26
     XK
    0.26
    ORM
    0.25
    ä¸ĭ游
    0.25
     unlocking
    0.24
    æ·Ģ
    0.24
    è´´åIJ§
    0.24
    ierarchy
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.