© 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. 10453
    Prev
    Next
    INDEX
    Explanations

    quality of

    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
    çIJĨæĥ³
    -0.10
    ëĿ½
    -0.10
    çļĦçIJĨæĥ³
    -0.09
    建ç«ĭåģ¥åħ¨
    -0.09
    å¼ĢæĿ¥
    -0.09
    è°Īè°Ī
    -0.09
    çªĹå¤ĸ
    -0.09
    ç¾İ好çĶŁæ´»
    -0.08
    elig
    -0.08
    ä¹IJè§Ĥ
    -0.08
    POSITIVE LOGITS
    -quality
    0.15
     quality
    0.15
    .quality
    0.13
    æķĻåŃ¦è´¨éĩı
    0.13
    quality
    0.13
     каÑĩеÑģÑĤво
    0.13
     Quality
    0.12
    è´¨éĩıåĴĮ
    0.12
    è´¨éĩı
    0.12
    çļĦè´¨éĩı
    0.12
    Activations Density 0.079%

    No Known Activations