© 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. 53905
    Prev
    Next
    INDEX
    Explanations

    comparing negative outcomes

    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
    天ä¸Ĭ
    -0.10
    声
    -0.09
    æ°´æµģ
    -0.09
    大åıij
    -0.09
    å¦ĩ
    -0.09
     обÑıзаÑĤелÑĮно
    -0.09
    ãģ©ãģĨãģĹãģ¦ãĤĤ
    -0.08
    ottage
    -0.08
    .Stack
    -0.08
    _helpers
    -0.08
    POSITIVE LOGITS
    èİ«è¿ĩäºİ
    0.12
     worse
    0.11
    èłķ
    0.10
    è¿ĺæľīä»Ģä¹Ī
    0.10
     worst
    0.09
     Worse
    0.09
    åħ³äºİæĪij们
    0.09
    è¿ĺæľīä¸ĢäºĽ
    0.09
    æĽ´è¦ģ
    0.09
    æĽ´å¤§çļĦ
    0.09
    Activations Density 0.040%

    No Known Activations