© 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. 35437
    Prev
    Next
    INDEX
    Explanations

    candy and sweets

    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
    鸡汤
    -0.11
    åķ¤éħĴ
    -0.11
    Beer
    -0.10
    iton
    -0.10
    ç¾ĬèĤī
    -0.09
     cocks
    -0.09
    模æĿ¿
    -0.09
     yard
    -0.09
     vegetables
    -0.09
    èĶ¬èıľ
    -0.09
    POSITIVE LOGITS
    ç»ıéĶĢ
    0.10
    å·§åħĭåĬĽ
    0.09
    æ´½
    0.09
    åĵģå°Ŀ
    0.09
    åŃ©åŃIJ们
    0.09
    窨
    0.09
    ä¹°åĪ°
    0.09
    åĮħè£ħ
    0.09
    享çĶ¨
    0.08
    è´®
    0.08
    Activations Density 0.051%

    No Known Activations