© 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. 18392
    Prev
    Next
    INDEX
    Explanations

    delighted to

    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¸ĭ车
    -0.10
    çĶļ
    -0.09
    æĥħ趣
    -0.09
    croft
    -0.09
    å«Įå¼ĥ
    -0.09
    å¬Ľ
    -0.09
    æķħ乡
    -0.09
    piar
    -0.08
    ç¾Ł
    -0.08
    æģIJæĥ§
    -0.08
    POSITIVE LOGITS
    [end
    0.09
    è¿ĺä¸įæĺ¯
    0.09
    tid
    0.08
     preliminary
    0.08
    è¿Ļä¸ĢåĪĩ
    0.08
     Riy
    0.08
    ä¹ĭä½Ļ
    0.08
    åħ¥éĢī
    0.08
    èĩªè±ª
    0.08
    æľīå¤ļ
    0.08
    Activations Density 0.013%

    No Known Activations