© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51894
    Prev
    Next
    INDEX
    Explanations

    shoots over Treasure, range efforts, in the post, moves around, knocked it, Hunter will

    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
    èĻİ
    -0.11
    aux
    -0.09
    æĺİæľĹ
    -0.08
    åľ°ä¸ĭ
    -0.08
    åĬ£
    -0.08
    æĭİ
    -0.08
    æµģåŁŁ
    -0.08
    å¯¹æľªæĿ¥
    -0.08
     Verm
    -0.08
    imei
    -0.08
    POSITIVE LOGITS
    欲
    0.10
    æĮij
    0.10
    raph
    0.09
    ancode
    0.09
    é¡¹çĽ®å»ºè®¾
    0.08
    ç«ĻçĿĢ
    0.08
    æĻļæľŁ
    0.08
    .bz
    0.08
    æ´¾
    0.08
    éĴµ
    0.08
    Activations Density 0.033%

    No Known Activations