© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 1193
    Prev
    Next
    INDEX
    Explanations

    words indicating transition or context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä»İæł¹æľ¬
    -0.09
    æµ·æ¹¾
    -0.08
    æĪijä¸įæĥ³
    -0.08
    çŁ¥å·±
    -0.08
    blas
    -0.08
     Lump
    -0.08
     complimentary
    -0.08
    æıIJåĢ¡
    -0.08
    èĩªçĦ¶æĺ¯
    -0.08
    æĦļ
    -0.08
    POSITIVE LOGITS
    æŃ»èĢħ
    0.10
    æŀģ大çļĦ
    0.09
    èµŃ
    0.09
    ãĥĪãĥª
    0.09
    é«ĺåħ´
    0.09
    çłĶ究æīĢ
    0.09
    æĸ°ä¸ī
    0.09
    è¦Ĩ
    0.09
    arged
    0.09
    .song
    0.08
    Activations Density 0.190%

    No Known Activations