© 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. 17162
    Prev
    Next
    INDEX
    Explanations

    Blazers, Le Mans, Chef, TripAdvisor

    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
    wake
    -0.10
    otal
    -0.10
    zelf
    -0.09
    ../../
    -0.09
    ling
    -0.09
    ÑĤал
    -0.09
    åIJĪèµĦ
    -0.09
     lå
    -0.09
    è±³
    -0.09
    tit
    -0.08
    POSITIVE LOGITS
    ä¸ļä½Ļ
    0.10
    èĵ¼
    0.10
    ries
    0.09
    æŀķ
    0.08
    人士
    0.08
    æŶè£ħ
    0.08
    ä¸ĵåĮº
    0.08
    oug
    0.08
    æ¸ļ
    0.08
     Lair
    0.08
    Activations Density 0.002%

    No Known Activations