© 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. 34271
    Prev
    Next
    INDEX
    Explanations

    maintain, renewal, continuing

    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
    çļĦçĭ¬çī¹
    -0.09
    èĬ½
    -0.09
    æĿł
    -0.09
    åįıå®ļ
    -0.09
    urtles
    -0.09
    ä¸ĢéĹª
    -0.09
    åħ¨å±Ģ
    -0.08
    çĭ¬çī¹
    -0.08
     Ty
    -0.08
     пÑĢÑıмо
    -0.08
    POSITIVE LOGITS
    æ¯ıå¹´
    0.15
    ç»´æĮģ
    0.14
     Renew
    0.14
    è¡°
    0.14
     renewal
    0.13
    ç»Ń
    0.13
    æ¯ıå¹´éĥ½
    0.13
    çºĮ
    0.12
    æ¯ıéļĶ
    0.12
    _REFRESH
    0.11
    Activations Density 0.102%

    No Known Activations