© 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. 6638
    Prev
    Next
    INDEX
    Explanations

    someone asking for help

    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
    TURE
    -0.10
    оÑģÑĮ
    -0.09
    æŁ¥çľĭæĽ´å¤ļ
    -0.09
    让æĤ¨
    -0.09
     Mahm
    -0.09
    æĬĦ
    -0.09
     беÑĢем
    -0.09
    alink
    -0.08
    çĸ¢
    -0.08
    partment
    -0.08
    POSITIVE LOGITS
    åı¯ä»¥
    0.12
    å®ĥåı¯ä»¥
    0.12
    èĥ½å¤Ł
    0.12
     can
    0.11
    æĺ¯åı¯ä»¥
    0.11
    åı¯ä»¥å¸®åĬ©
    0.11
    èĥ½å¤ł
    0.10
    è¿ĺèĥ½
    0.10
    ä¹Łèĥ½
    0.10
    åı¯ä»¥ä»İ
    0.10
    Activations Density 0.216%

    No Known Activations