© 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. 26538
    Prev
    Next
    INDEX
    Explanations

    first end / first search

    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
    nist
    -0.10
    æľŁåĨħ
    -0.09
    鸣
    -0.09
    ä½Ĩ她
    -0.09
    ä¼İ
    -0.09
    æµģæ°´
    -0.08
    çĤ¹è¯Ħ
    -0.08
    ÑĤем
    -0.08
    æľºåĬ¨
    -0.08
    åįģäºĮäºĶ
    -0.08
    POSITIVE LOGITS
    éĿ¢å¯¹éĿ¢
    0.09
    æļĤåģľ
    0.09
    TPL
    0.09
     Mant
    0.09
    æ²¾
    0.09
    oli
    0.09
    ias
    0.08
    çļĦæĥħå½¢
    0.08
    ä¸Ģ线
    0.08
    åıijçİ°
    0.08
    Activations Density 0.091%

    No Known Activations