© 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. 31961
    Prev
    Next
    INDEX
    Explanations

    chain fatty

    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
    çķ¶æĤ¨åľ¨
    -0.09
    èĥĥåı£
    -0.09
    èĢģçĪ·
    -0.09
    æĨĭ
    -0.08
    浸
    -0.08
    ìĩł
    -0.08
    èĢģçĪ·åŃIJ
    -0.08
    flate
    -0.08
     ÐIJлекÑģан
    -0.08
    electron
    -0.08
    POSITIVE LOGITS
    ç¾İå¦Ĩ
    0.10
    æĬ¤èĤ¤
    0.10
    ç¾İçĻ½
    0.10
    è¿Ļ款
    0.10
     пÑĢодÑĥк
    0.09
     Dol
    0.09
     dol
    0.09
    使çĶ¨èĢħ
    0.09
    æ³ķ令
    0.09
    ä¿Ŀ湿
    0.09
    Activations Density 0.064%

    No Known Activations