© 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. 31395
    Prev
    Next
    INDEX
    Explanations

    contrasting questions or statements

    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
    诱人
    -0.10
     tim
    -0.10
    æĸ°æĶ¿
    -0.09
    è±³
    -0.08
    宣称
    -0.08
    ä¼ĺæĥłæĶ¿çŃĸ
    -0.08
    éĵĹ
    -0.08
    éĿłçĿĢ
    -0.08
    ä¹ĭæĦı
    -0.08
    ç¼ķ
    -0.08
    POSITIVE LOGITS
    ınd
    0.09
    icc
    0.09
    icie
    0.09
    ifest
    0.09
    åį´ä¸į
    0.09
    åIJĪçIJĨæĢ§
    0.08
    ç«ĭåį³
    0.08
    ëĤľ
    0.08
    inoa
    0.08
    æ¡Į
    0.08
    Activations Density 0.131%

    No Known Activations