© 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. 34224
    Prev
    Next
    INDEX
    Explanations

    bed bugs, aries increment, calls have, iaozi, flaming

    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
    ä¹°çļĦ
    -0.10
    马路
    -0.09
    æĥ¯ä¾ĭ
    -0.09
    çĩĬ
    -0.09
    Êı
    -0.09
     peru
    -0.09
    æĸŃ
    -0.09
    ä¸įå¼Ģ
    -0.09
    à¸Ĭà¸Ļ
    -0.09
    èĶļ
    -0.08
    POSITIVE LOGITS
    便
    0.10
    ç»
    0.10
     unf
    0.09
    大æĸ¹
    0.08
    çļĦèģĮä¸ļ
    0.08
     Jak
    0.08
    产æĿĥ
    0.08
    è¹ĩ
    0.08
     relaxed
    0.08
    _lex
    0.08
    Activations Density 0.022%

    No Known Activations