© 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. 38694
    Prev
    Next
    INDEX
    Explanations

    Perez, Lasorda, Wieters

    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
    zie
    -0.09
    wort
    -0.09
    宾
    -0.08
    ude
    -0.08
    CEPT
    -0.08
    è¿Ļ个æĹ¶ä»£
    -0.08
    èįı
    -0.08
    adel
    -0.08
     lun
    -0.07
    spath
    -0.07
    POSITIVE LOGITS
    é¾Ľ
    0.09
    éĵ¡
    0.09
    yr
    0.09
    åĨ¼
    0.09
     зак
    0.09
    åģľä¸ĭ
    0.09
    \Twig
    0.09
    å·©
    0.08
    æĶ¾ä¸ĭ
    0.08
    Dispose
    0.08
    Activations Density 0.006%

    No Known Activations