© 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. 56346
    Prev
    Next
    INDEX
    Explanations

    not sure

    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
    èĩªçĦ¶æĺ¯
    -0.10
    æĪIJ为ä¸Ģ个
    -0.10
    è¿ĺæĺ¯ä¼ļ
    -0.09
    öl
    -0.09
    伤å¿ĥ
    -0.09
    å½ĵçĦ¶æĺ¯
    -0.09
     лиÑĪ
    -0.09
    éļIJèĹı
    -0.09
    温æĥħ
    -0.09
    ipl
    -0.09
    POSITIVE LOGITS
     sure
    0.15
    ä¸įç¡®å®ļ
    0.13
    sure
    0.13
    ä¸įæ¸ħæ¥ļ
    0.12
     unsure
    0.12
     certainty
    0.12
    æĺİç¡®
    0.11
    æ¸ħæ¥ļ
    0.11
    Sure
    0.11
     Sure
    0.10
    Activations Density 0.095%

    No Known Activations