© 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. 6560
    Prev
    Next
    INDEX
    Explanations

    hurricane season

    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
    ÙĤات
    -0.10
    знак
    -0.10
     TestCase
    -0.10
    æĪIJ份
    -0.09
    缴åįĩ
    -0.09
    StepThrough
    -0.09
    åijĨ
    -0.09
    éĺ¶
    -0.08
    å¼Ł
    -0.08
    æŀ¶
    -0.08
    POSITIVE LOGITS
     season
    0.17
     seasons
    0.15
    ãĤ·ãĥ¼ãĤºãĥ³
    0.14
     Ñģезон
    0.14
    èµĽåŃ£
    0.14
     Ñģез
    0.13
    åŃ£
    0.13
    åŃ£èĬĤ
    0.13
    _season
    0.12
    season
    0.12
    Activations Density 0.148%

    No Known Activations