© 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. 2036
    Prev
    Next
    INDEX
    Explanations

    through

    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
    大éĿ¢ç§¯
    -0.11
    çĭIJ
    -0.09
    æ³ķå®ĺ
    -0.09
    éļİ
    -0.09
    滩
    -0.09
    ignum
    -0.08
    finalize
    -0.08
    ä¸įå¿ĺ
    -0.08
    屯
    -0.08
    ÑģÑĥд
    -0.08
    POSITIVE LOGITS
    æįı
    0.11
    å©¿
    0.10
    æ¡ħ
    0.10
    _ACTIV
    0.09
    ÑĨеп
    0.09
    neau
    0.09
    æµĵ缩
    0.09
    çĿ£å¯¼
    0.09
     Maher
    0.09
     Boyd
    0.09
    Activations Density 0.061%

    No Known Activations