© 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. 35049
    Prev
    Next
    INDEX
    Explanations

    Toyota model names

    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
    å¼łå®¶åı£
    -0.11
    çİ»çĴĥ
    -0.09
     Rooney
    -0.09
     Ñģог
    -0.09
    æŀ³
    -0.09
    ä¸ĵ人
    -0.09
     rol
    -0.08
     Glass
    -0.08
    usat
    -0.08
    æĬ¥å¤į
    -0.08
    POSITIVE LOGITS
    éĦŀ
    0.11
    丰çĶ°
    0.10
    åľ¨æĹ¥æľ¬
    0.10
     Loft
    0.09
    æĭ¥
    0.09
    纵åIJij
    0.09
    bose
    0.09
    è®®
    0.08
    æľĿ
    0.08
    汤
    0.08
    Activations Density 0.008%

    No Known Activations