© 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. 17863
    Prev
    Next
    INDEX
    Explanations

    waste of time and resources

    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
    éĢĤæŶ
    -0.11
    ç¨įç¨į
    -0.11
    被æīĵ
    -0.11
    çļĦ姿æĢģ
    -0.10
    HEL
    -0.10
    ç§Łè½¦
    -0.09
    æīĭæİĮ
    -0.09
    æĸĩåĮĸèīºæľ¯
    -0.09
    æĿ¥çľĭçľĭ
    -0.09
    è¾ĺ
    -0.09
    POSITIVE LOGITS
    æīİ
    0.09
     بد
    0.08
    å¼ģ
    0.08
    cus
    0.08
    äºį
    0.08
     Gavin
    0.08
    ger
    0.08
    Õ¬
    0.08
    otime
    0.08
    åŃĺéĩı
    0.08
    Activations Density 0.024%

    No Known Activations