© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 887
    Prev
    Next
    INDEX
    Explanations

    frostbite, brushing, avoid feeding, planting resistant, tips to

    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
    è¿ĻåĿĹ
    -0.10
    uary
    -0.10
    opal
    -0.09
    æ»Ĺ
    -0.09
    pek
    -0.09
    人æ°ijåĮ»éĻ¢
    -0.09
    Ñħо
    -0.09
    ippet
    -0.09
    è£ħ
    -0.09
    vik
    -0.08
    POSITIVE LOGITS
    èįŁ
    0.09
    嵩
    0.08
    åįĪåIJİ
    0.08
    æĹ©çĤ¹
    0.08
    äºĨ解
    0.08
    级以ä¸Ĭ
    0.08
    èį¦
    0.08
    äºĭåħĪ
    0.08
    å´¦
    0.08
    inely
    0.08
    Activations Density 0.028%

    No Known Activations