© 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. 25-TRANSCODER-HP
    7. 109338
    Prev
    Next
    INDEX
    Explanations

    non-English words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    eel
    -0.30
    åĿĢ
    -0.29
    mans
    -0.28
    ä¸İä¼Ĺ
    -0.26
     alleg
    -0.26
     onward
    -0.26
    enberg
    -0.25
    mong
    -0.24
    麽
    -0.24
    malink
    -0.24
    POSITIVE LOGITS
    åĩ¡
    0.25
    æĬĺ
    0.25
    ewhere
    0.25
    失败
    0.24
     STILL
    0.23
    åĽºå®ļçļĦ
    0.23
    ãĤĤãģ£ãģ¨
    0.23
    æ¶Ī失
    0.23
    ãĤĴãģĹãģ¦ãģĦãĤĭ
    0.23
     bại
    0.23
    Activations Density 0.231%

    No Known Activations