© 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. 29958
    Prev
    Next
    INDEX
    Explanations

    systematic evaluation, compilation, review

    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
    æ´ĹåĩĢ
    -0.10
    wyn
    -0.09
    çŀ©çĽ®
    -0.08
    è§ģæķĪ
    -0.08
    اÙħÙĬ
    -0.08
    ä¹İ
    -0.08
    人人
    -0.08
    å®ļäºĨ
    -0.08
    vest
    -0.08
    еÑĩ
    -0.08
    POSITIVE LOGITS
    ALLY
    0.11
    çªķ
    0.09
    çĽ¸ä¼ł
    0.09
    滥
    0.09
    ä¸į妨
    0.09
    -minded
    0.08
    chai
    0.08
    ä¸įç®¡ä½ł
    0.08
    rub
    0.08
    éĥİ
    0.08
    Activations Density 0.038%

    No Known Activations