© 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. 63614
    Prev
    Next
    INDEX
    Explanations

    climatic variability and extreme weather

    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
    å¾ģ
    -0.11
    æī©
    -0.10
    iets
    -0.10
    ä¿¡èªī
    -0.09
    æĭ¥
    -0.09
    æį£
    -0.09
    æ¼±
    -0.09
    两åįĥ
    -0.09
     crush
    -0.09
    使æĪij
    -0.09
    POSITIVE LOGITS
    æ¡Ģ
    0.08
    _FRE
    0.08
    Old
    0.08
    éĢĤå®ľ
    0.07
    æĽ©
    0.07
     drought
    0.07
    ä¹łæĥ¯äºĨ
    0.07
    çĤ³
    0.07
    ornado
    0.07
    æĴ¬
    0.07
    Activations Density 0.076%

    No Known Activations