© 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. 88454
    Prev
    Next
    INDEX
    Explanations

    document lengths and sizes

    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
    èĸ®
    -0.28
    è¿Ļæł·ä¸Ģ个
    -0.28
    _pixels
    -0.27
     Dil
    -0.27
    ¢åįķ
    -0.26
    éĹª
    -0.26
    æ¿¡
    -0.25
    ijk
    -0.25
    ãĤīãĤĮãģ¾ãģĻ
    -0.25
    常
    -0.24
    POSITIVE LOGITS
     MAY
    0.30
     optional
    0.28
    innie
    0.26
     missing
    0.24
    å·®å¼Ĥ
    0.24
     half
    0.24
    èĩ³å°ij
    0.23
     group
    0.23
     bor
    0.23
     ?:
    0.23
    Activations Density 0.004%

    No Known Activations