© 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. 19140
    Prev
    Next
    INDEX
    Explanations

    comparisons using 'than'

    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»ŀ
    -0.11
    éĵ²
    -0.09
    .setter
    -0.09
    ett
    -0.08
    ä¸įå°ı
    -0.08
    çķħ
    -0.08
    _dll
    -0.08
    ä½ĵåŀĭ
    -0.08
    ç»ıæµİæįŁå¤±
    -0.08
    icht
    -0.08
    POSITIVE LOGITS
    çĨı
    0.10
    ä¼ĺæĥł
    0.10
     superior
    0.10
    æĪĸå¤ļ
    0.10
    馥
    0.10
     Better
    0.10
    åij¸
    0.10
    ä¼ĺè¶Ĭ
    0.09
    å¥Ĥ
    0.09
    æĽ´å¥½çļĦ
    0.09
    Activations Density 0.094%

    No Known Activations