© 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. 22592
    Prev
    Next
    INDEX
    Explanations

    always had

    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
     currently
    -0.12
    å½ĵä»Ĭ
    -0.10
    ä¾ĿçĦ¶æĺ¯
    -0.10
    currently
    -0.10
    缮åīįæŃ£åľ¨
    -0.10
    缮åīį
    -0.10
    æŃ£åľ¨è¿Ľè¡Į
    -0.10
    继ç»Ńä¿ĿæĮģ
    -0.10
    ä¾Ŀæŧæĺ¯
    -0.10
    åīįä¸įä¹ħ
    -0.10
    POSITIVE LOGITS
    è¾ĥ大çļĦ
    0.10
    ä¸Ģ缴éĥ½
    0.10
    ä¸Ģ缴æĺ¯
    0.09
    åħ¢
    0.08
    pest
    0.08
    зи
    0.08
    éĤ£æŶåĢĻ
    0.08
    罩
    0.08
    娥
    0.08
    oser
    0.08
    Activations Density 0.074%

    No Known Activations