© 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. 51144
    Prev
    Next
    INDEX
    Explanations

    Go for it / Go and

    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
    çĤ¬
    -0.09
    ä¸ĭæĿ¥
    -0.09
    ç½ijç»ľä¼łæĴŃ
    -0.09
    åĽ½ç«ĭ
    -0.08
    æµĵ
    -0.08
     goodbye
    -0.08
    ingo
    -0.08
     Ngô
    -0.08
    åľ¨æł¡
    -0.08
    客æ°Ķ
    -0.08
    POSITIVE LOGITS
    大æĸ¹
    0.10
    群ä½ĵ
    0.10
    oga
    0.09
    èĥª
    0.09
    åĴı
    0.09
    OE
    0.09
    éŃģ
    0.09
    æĬĵä½ı
    0.08
    大éģĵ
    0.08
    à¸Ĭà¸Ļ
    0.08
    Activations Density 0.010%

    No Known Activations