© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 86787
    Prev
    Next
    INDEX
    Explanations

    math and programming equations

    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
    Negative Logits
    west
    -0.27
    æ³ķåĪĻ
    -0.27
    æ¹į
    -0.26
     Engine
    -0.25
    aub
    -0.24
    apist
    -0.24
    ῦ
    -0.24
    sun
    -0.24
     engine
    -0.24
    ÑĤелÑĮ
    -0.24
    POSITIVE LOGITS
     каÑĢ
    0.28
    ä¸Ģæł·
    0.28
    çł»
    0.27
    <Route
    0.26
    ä¸Ģæŀ¶
    0.25
    éĤ£ä»½
    0.25
    ä¸Ģ樣
    0.25
    ä¸Ģç¬Ķ
    0.24
    ä¸Ģ份
    0.24
    åı¦ä¸ĢåįĬ
    0.24
    Activations Density 0.011%

    No Known Activations