© 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. 55201
    Prev
    Next
    INDEX
    Explanations

    I

    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
    inde
    -0.12
    linky
    -0.09
    æ´»å¾Ĺ
    -0.09
    ç½¢äºĨ
    -0.09
    çĭŃ
    -0.08
    ele
    -0.08
    好ä¸į容æĺĵ
    -0.08
    è¶Ĭæĺ¯
    -0.08
    LU
    -0.08
     indeed
    -0.08
    POSITIVE LOGITS
    ä¸įçŁ¥éģĵ
    0.26
    ä¸įæ¸ħæ¥ļ
    0.25
    æĪijä¸įçŁ¥éģĵ
    0.24
    ä¸įçŁ¥
    0.22
    æľªçŁ¥
    0.20
    ä¹Łä¸įçŁ¥éģĵ
    0.20
    éĥ½ä¸įçŁ¥éģĵ
    0.19
     unknown
    0.19
    ä¸įç¡®å®ļ
    0.17
     unclear
    0.16
    Activations Density 0.229%

    No Known Activations