© 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. 37565
    Prev
    Next
    INDEX
    Explanations

    describing odd or unusual situations

    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
     íĺ¸
    -0.09
    -kit
    -0.08
    æģĤ
    -0.08
    ANGO
    -0.08
    èĻ
    -0.08
    è¿Ļ次
    -0.08
    æĥħåĨµè¿Ľè¡Į
    -0.08
    ùng
    -0.08
    hop
    -0.08
    icher
    -0.08
    POSITIVE LOGITS
    æľ¬äºº
    0.10
    没éĶĻ
    0.10
    è¿ĺ羣
    0.10
     знаÑĩиÑĤ
    0.10
    ä¸į代表
    0.10
    äºĮåŃĹ
    0.10
    è¿Ļ个è¯į
    0.09
    åı¯è§Ĥ
    0.09
    å¹²åĺĽ
    0.09
     indeed
    0.09
    Activations Density 0.144%

    No Known Activations