© 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. 33972
    Prev
    Next
    INDEX
    Explanations

    thanks 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
    æĸ°æĹ¶æľŁ
    -0.12
    åıªè¦ģæľī
    -0.10
    ãģıãĤĭ
    -0.10
    å·¥ç¨ĭé¡¹çĽ®
    -0.09
    èѬå¦Ĥ
    -0.09
    åĽłä¸ºå¥¹
    -0.09
    åľŃ
    -0.09
    инг
    -0.09
    [to
    -0.09
    ree
    -0.09
    POSITIVE LOGITS
    è¿Ļç§įæĸ¹å¼ı
    0.09
    isko
    0.08
    ermann
    0.08
    даÑĢ
    0.08
     moll
    0.08
    æłª
    0.08
    æĢĻ
    0.08
    achel
    0.08
     Wolff
    0.08
    opol
    0.07
    Activations Density 0.008%

    No Known Activations