© 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. 35434
    Prev
    Next
    INDEX
    Explanations

    in people or animals

    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
    对åѦçĶŁ
    -0.11
    对åŃ©åŃIJ
    -0.10
    çĶľèľľ
    -0.09
    ulan
    -0.09
    让æ¶Īè´¹èĢħ
    -0.09
    è¢ĭåŃIJ
    -0.08
    å«Ĥ
    -0.08
    æ®·
    -0.08
    CTest
    -0.08
    ovich
    -0.08
    POSITIVE LOGITS
    ä»»ä½ķ人
    0.12
    æĪIJ年人
    0.11
     Ñĩеловека
    0.11
    æīĢæľī人
    0.10
     individuals
    0.10
    广大
    0.10
     younger
    0.10
     adults
    0.10
    æ¯ıä¸Ģ个人
    0.10
    æ¯ıä¸Ģä½į
    0.10
    Activations Density 0.788%

    No Known Activations