© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51522
    Prev
    Next
    INDEX
    Explanations

    patient endurance and tolerance

    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
    athe
    -0.08
     кÑĢÑĥ
    -0.08
     lazy
    -0.08
    æĩĤ
    -0.08
     Rat
    -0.08
    çĿ¬
    -0.08
    folio
    -0.08
     laz
    -0.07
     rat
    -0.07
     ing
    -0.07
    POSITIVE LOGITS
    å¿įåıĹ
    0.22
    å¿į
    0.18
    容å¿į
    0.16
    æī¿åıĹ
    0.14
    tol
    0.14
     toler
    0.14
     tolerate
    0.13
    à¸Ĺà¸Ļ
    0.12
     tolerated
    0.12
     tolerance
    0.11
    Activations Density 0.034%

    No Known Activations