© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7517
    Prev
    Next
    INDEX
    Explanations

    mob boss, mafia member

    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
    æī¹åıijå¸Ĥåľº
    -0.10
    çļĦæĢģ度
    -0.10
     اÙĦعÙħ
    -0.09
    urate
    -0.09
    社ä¼ļåĮĸ
    -0.09
    æĺ¯ä¸įä¼ļ
    -0.08
    æºħ
    -0.08
    æ³¼
    -0.08
     Vand
    -0.08
    ision
    -0.08
    POSITIVE LOGITS
    ÑģÑĤан
    0.09
     Hutch
    0.09
    ä¾Ŀæ³ķ追究
    0.09
    æ¯ĭ
    0.08
    REFERENCE
    0.08
    æĸĩåĮĸæĹħ游
    0.08
    浩
    0.08
    anity
    0.08
    é¹ħ
    0.08
    ALK
    0.08
    Activations Density 0.011%

    No Known Activations