© 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. 50772
    Prev
    Next
    INDEX
    Explanations

    language names

    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
    çļİ
    -0.09
    ç»Ħ建
    -0.09
    æµ·å¤ĸ
    -0.09
    çĸµ
    -0.09
    æī¾åĽŀ
    -0.09
    èĭ±æĸĩ
    -0.09
    éĻŁ
    -0.09
    åĽŀæĶ¶
    -0.09
    åĽ½éĻħåIJĪä½ľ
    -0.08
    èĢģ乡
    -0.08
    POSITIVE LOGITS
    主è¦ģçĶ¨äºİ
    0.10
    æģ©
    0.09
    书éĿ¢
    0.09
    åįĥä¸ĩ
    0.09
     spoken
    0.09
    spoken
    0.08
    setUp
    0.08
    åĴĮåħ¶ä»ĸ
    0.08
    _used
    0.08
    metis
    0.08
    Activations Density 0.189%

    No Known Activations