© 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. 2581
    Prev
    Next
    INDEX
    Explanations

    ang followed by Filipino words

    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
    å°±è¿Ļæł·
    -0.10
    å°±æĺ¯è¿Ļæł·
    -0.10
    ä¸Ģæĸ¹éĿ¢æĺ¯
    -0.10
    ä¸Ńåħ³
    -0.09
    å°±è¿Ļä¹Ī
    -0.09
    åİŁåĪĻä¸Ĭ
    -0.09
     comps
    -0.09
    PACE
    -0.09
    ç³Ĭæ¶Ĥ
    -0.09
    çľ¼ä¸ĭ
    -0.09
    POSITIVE LOGITS
    åıij表
    0.09
    erner
    0.09
    æ³Ľ
    0.08
    管çIJĨåĴĮ
    0.08
    è¾ĥ强çļĦ
    0.08
    inals
    0.08
    好è¿IJ
    0.08
    ifu
    0.08
    ented
    0.08
    ÑĢÑĭ
    0.07
    Activations Density 0.006%

    No Known Activations