© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21362
    Prev
    Next
    INDEX
    Explanations

    shed some light on

    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
    èĢ
    -0.10
    ricula
    -0.10
     Ñĥни
    -0.09
    æĶ¯æĴij
    -0.08
    楼å®ĩ
    -0.08
    羣
    -0.08
    æŁ¥çľĭæĽ´å¤ļ
    -0.08
    è¸
    -0.08
    à¸Ńà¸ģ
    -0.08
     spo
    -0.08
    POSITIVE LOGITS
    çĽı
    0.10
    enment
    0.10
    æ²ı
    0.10
    çħ§äº®
    0.09
    çģ¯
    0.09
    é¹Ń
    0.09
    éĹªéĹª
    0.09
    licht
    0.09
    LIGHT
    0.08
    é»ijæļĹ
    0.08
    Activations Density 0.020%

    No Known Activations