© 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. 5177
    Prev
    Next
    INDEX
    Explanations

    dog behavior

    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
    é«ĺä»·
    -0.12
    çľģéĴ±
    -0.11
    é¹ŀ
    -0.10
    让åŃ©åŃIJ
    -0.09
    çķ¸
    -0.09
    æħİ
    -0.09
    avic
    -0.09
    æįı
    -0.09
    ç¦ģ
    -0.09
    ÙĦج
    -0.09
    POSITIVE LOGITS
    主人
    0.13
    ç»ĻæĪij们
    0.09
    åįĩéĻį
    0.09
    åİ¿åŁŁ
    0.09
    对æĪij们
    0.09
    顽
    0.09
    ç»Ī身
    0.09
    çĭIJ
    0.09
    çļĦçľ¼ç¥ŀ
    0.09
     mate
    0.09
    Activations Density 0.067%

    No Known Activations