© 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. 112869
    Prev
    Next
    INDEX
    Explanations

    you

    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
    äºĨ解ä¸Ģä¸ĭ
    -0.28
    ä»ĭåħ¥
    -0.27
    utherland
    -0.27
    ãĤ¤ãĥ³ãĤ¿ãĥ¼ãĥ
    -0.26
    æĺ¯åIJ¦åŃĺåľ¨
    -0.26
    (Gravity
    -0.25
    endant
    -0.25
     Council
    -0.25
    æ¦Ĩ
    -0.24
    æĪĸå°Ĩ
    -0.24
    POSITIVE LOGITS
    åıĮåıĮ
    0.30
    stances
    0.27
    zá
    0.27
    请åıĬæŶ
    0.26
    æīĢå¾Ĺ
    0.25
    zon
    0.25
    isé
    0.25
    â½¼
    0.25
    åĿļ
    0.24
     Humb
    0.24
    Activations Density 0.002%

    No Known Activations