© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 22257
    Prev
    Next
    INDEX
    Explanations

    names like Hoff, von Feld, Lund

    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
    igne
    -0.09
    è¹Ĭ
    -0.09
    æŁıæŀĹ
    -0.08
    åĽ½ä¼ļ
    -0.08
    ONS
    -0.08
    ç»Ĥ
    -0.08
    äºĨä¸Ģåı¥
    -0.08
    ä¸ĩåħĥ以ä¸Ĭ
    -0.08
    ubo
    -0.08
    onom
    -0.08
    POSITIVE LOGITS
    é¢Ĩ导
    0.10
    lage
    0.09
    鸩
    0.09
    éŨåı£
    0.09
    ishing
    0.09
    lords
    0.09
    anova
    0.08
    ãģĹãģ¾ãģĨ
    0.08
    æ¯ıä¸Ģ次
    0.08
    ÙĪع
    0.08
    Activations Density 0.014%

    No Known Activations