© 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. 62124
    Prev
    Next
    INDEX
    Explanations

    scoring goals

    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
    åĩĮæĻ¨
    -0.10
    å¤ļ人
    -0.09
    èł¢
    -0.08
    åģĮ
    -0.08
    éŀĺ
    -0.08
    -prev
    -0.08
    åĩ¡äºĭ
    -0.08
    åĽ½æľī
    -0.08
     recre
    -0.07
    loi
    -0.07
    POSITIVE LOGITS
    è´¯
    0.10
    çĤ¯
    0.10
     unheard
    0.10
    è¿Ļä¸Ģå¹´
    0.10
    æį®ç»Łè®¡
    0.10
    colo
    0.09
     pon
    0.09
    æ´Ĵ
    0.09
    产éĩı
    0.09
    åIJİæİĴ
    0.09
    Activations Density 0.075%

    No Known Activations