© 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. 27-TRANSCODER-HP
    7. 58561
    Prev
    Next
    INDEX
    Explanations

    code and math

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    è¶ĬæĿ¥
    -0.28
    arkan
    -0.28
    çIJĨ解åĴĮ
    -0.27
    è°Ģ
    -0.27
    anka
    -0.25
     emotionally
    -0.25
    çĹ´
    -0.24
    å·¡è§Ĩ
    -0.24
    ä¸įæĸŃæī©å¤§
    -0.24
    bie
    -0.24
    POSITIVE LOGITS
     lé
    0.30
    常
    0.27
    *log
    0.26
    æݨåIJij
    0.25
    éĩijåĪļ
    0.25
     водо
    0.25
    kö
    0.24
    rieb
    0.24
    æİ
    0.24
    èķ´
    0.24
    Activations Density 0.008%

    No Known Activations