© 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. 63009
    Prev
    Next
    INDEX
    Explanations

    qualities or descriptions following 'are'/'is'

    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
    å¼Ħ
    -0.09
    ynchronously
    -0.09
     Hab
    -0.08
    illon
    -0.08
    æ¿Ģ
    -0.08
    ä¸ĵéŨ
    -0.08
    ä¸Ģè¡Į
    -0.08
    enth
    -0.08
     waived
    -0.08
    æľ¬èº«å°±æĺ¯
    -0.08
    POSITIVE LOGITS
    大å¤ļ
    0.13
    大å¤ļæĺ¯
    0.11
    çļĦè´¨éĩı
    0.10
    åĩ¡æĺ¯
    0.10
    åĿĩçĶ±
    0.09
     quality
    0.09
    åŁºæľ¬ä¸Ĭéĥ½
    0.09
    æĿ¥èĩª
    0.09
    è·Łä»ĸ
    0.09
    è´¨éĩı管çIJĨ
    0.09
    Activations Density 0.144%

    No Known Activations