© 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. 11762
    Prev
    Next
    INDEX
    Explanations

    look at the

    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
    è°ģçŁ¥éģĵ
    -0.10
    æ¡Ģ
    -0.09
    /as
    -0.09
    éĵ¤
    -0.09
    æıļ
    -0.08
    ä½łçŁ¥éģĵ
    -0.08
    PathComponent
    -0.08
    zion
    -0.08
     Lone
    -0.08
    ÙĬرا
    -0.08
    POSITIVE LOGITS
    æķ´ä¸ª
    0.10
    å¤ľéĩĮ
    0.09
    OrElse
    0.09
    å¸Ĥåľºä¸Ĭ
    0.09
    éĥ½å¾Ī
    0.08
    ä»ĸæĽ¾
    0.08
    strup
    0.08
    Ñĩин
    0.08
    ä¸įæĺ¯å¾Ī
    0.08
    åıijå±ķæĪĺçķ¥
    0.08
    Activations Density 0.051%

    No Known Activations