© 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. 55264
    Prev
    Next
    INDEX
    Explanations

    collectively or together

    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
    åĨį说
    -0.10
    æľ¬èº«å°±æĺ¯
    -0.08
    æľ¬èº«
    -0.08
    [âĢ¦]
    -0.08
    gons
    -0.08
    缴éĢļ车
    -0.08
    plit
    -0.08
    ederation
    -0.08
    æ¯ıå¹´éĥ½
    -0.08
    éĥ½è¯´
    -0.07
    POSITIVE LOGITS
    èµ·ä¾Ĩ
    0.11
    å½¢æĪIJäºĨ
    0.11
    æŀĦæĪIJäºĨ
    0.11
    被称为
    0.10
    èµ·æĿ¥
    0.10
    å®ĮæĪIJåIJİ
    0.10
    æ¯Ķè¾ĥ好
    0.10
    æį£
    0.09
    建ç«ĭèµ·
    0.09
    责令
    0.09
    Activations Density 0.040%

    No Known Activations