© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19757
    Prev
    Next
    INDEX
    Explanations

    all rights reserved

    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
    æĹłæĥħ
    -0.11
    æĸŃ
    -0.09
    Promise
    -0.09
    .addTab
    -0.09
    天æ°Ķ
    -0.08
     promise
    -0.08
    微信
    -0.08
    微信åħ¬ä¼Ĺ
    -0.08
    æľīå¤ļå°ij
    -0.08
    è·ijåĪ°
    -0.08
    POSITIVE LOGITS
    å°ķ
    0.10
    æ®Ĩ
    0.09
    ç«ĭæ¡Ī
    0.09
    ä¸ĢåĪĩ
    0.09
    ıl
    0.09
    ÇĴ
    0.08
    lö
    0.08
    omid
    0.08
    icious
    0.08
    å²·
    0.08
    Activations Density 0.090%

    No Known Activations