© 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. 2526
    Prev
    Next
    INDEX
    Explanations

    rapid freezing, slow thawing

    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
    æijĩ
    -0.09
    æ»Ł
    -0.09
    åİ»åĮ»éĻ¢
    -0.09
    æĻ®éĢļè¯Ŀ
    -0.09
    çĸı
    -0.08
    æĻĥ
    -0.08
    壳
    -0.08
    èĥ½åľ¨
    -0.08
    åIJ¸
    -0.08
    éĩįçĹĩ
    -0.08
    POSITIVE LOGITS
    å°ĸ
    0.10
    ä»»ä½ķ人éĥ½
    0.09
    arella
    0.09
    ä¹Įé²ģæľ¨é½IJ
    0.09
    éªŀ
    0.09
    ä¸İä¸ŃåĽ½
    0.09
    ç¿°
    0.08
    ç¯ģ
    0.08
     occurrences
    0.08
    ocular
    0.08
    Activations Density 0.043%

    No Known Activations