© 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. 7251
    Prev
    Next
    INDEX
    Explanations

    in or inside

    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
    ä¼ı
    -0.10
    oga
    -0.09
    ç«¥
    -0.09
    usc
    -0.08
    建档
    -0.08
     воÑĤ
    -0.08
    åĩĢæ°´
    -0.08
    ayah
    -0.08
    骼
    -0.08
    è¿Ļä¹Īåģļ
    -0.08
    POSITIVE LOGITS
    åľ¨éĩĮéĿ¢
    0.15
     therein
    0.13
    åŃIJéĩĮ
    0.11
    éĩĮéĿ¢
    0.11
     ÑģодеÑĢжа
    0.10
    ä¹ĭä¸Ń
    0.09
    裡éĿ¢
    0.09
    éĶ·
    0.09
    纳
    0.09
    éĩĮéĿ¢æľī
    0.09
    Activations Density 0.130%

    No Known Activations