© 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. 31454
    Prev
    Next
    INDEX
    Explanations

    prepositions indicating time or sequence

    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
     horm
    -0.08
    ented
    -0.08
    entric
    -0.08
     forKey
    -0.08
    ä¹Ļ
    -0.08
    éĿŀ常好çļĦ
    -0.07
     Carroll
    -0.07
    èį£å¹¸
    -0.07
     throttle
    -0.07
    Attempt
    -0.07
    POSITIVE LOGITS
    æľ¬æĬ¥è®°èĢħ
    0.10
    appen
    0.09
    azon
    0.09
    åħ¨çIJĥæľĢ大
    0.09
    ios
    0.09
    èĴ¸
    0.09
    ãģ¨ãģĦãģĨãģĵãģ¨
    0.09
    ãĤ³ãĥ¡ãĥ³ãĥĪ
    0.09
    æѤäºĭ
    0.08
    æѤæ¡Ī
    0.08
    Activations Density 0.062%

    No Known Activations