© 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. 10310
    Prev
    Next
    INDEX
    Explanations

    sports competitions and seasons

    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
    blade
    -0.09
     Mour
    -0.09
    batim
    -0.09
    å¯ĵ
    -0.09
    ritz
    -0.09
    å°ıå·§
    -0.08
    ORED
    -0.08
    bjerg
    -0.08
    佬
    -0.08
    åIJį称
    -0.08
    POSITIVE LOGITS
    å±ıå¹ķä¸Ĭ
    0.10
    ç»ļ
    0.09
    失åĪ©
    0.08
    æĥĨ
    0.08
    -money
    0.08
    sWith
    0.08
     Hutchinson
    0.08
    æį§
    0.08
    çĶ·å¥³
    0.08
    èĬľ
    0.08
    Activations Density 0.146%

    No Known Activations