© 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. 21905
    Prev
    Next
    INDEX
    Explanations

    dedication, options, costs

    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
    å¾Ī好çļĦ
    -0.12
    è¾ĥé«ĺçļĦ
    -0.11
    è¾ĥ好çļĦ
    -0.11
    å¾Īé«ĺçļĦ
    -0.10
    好çļĦ
    -0.09
    ãģĭãĤĤãģĹãĤĮãģ¾ãģĽãĤĵãģĮ
    -0.09
    çļĦèī¯å¥½
    -0.09
    çIJĨæĥ³çļĦ
    -0.09
    å¾Īä¹ħ
    -0.08
    ç¼ĸåı·
    -0.08
    POSITIVE LOGITS
    ç®Ģ缴æĺ¯
    0.15
    ç®Ģ缴
    0.13
    羣æĺ¯
    0.11
    éĨ®
    0.11
    æĮ½
    0.11
    ç®ĢçĽ´å°±æĺ¯
    0.11
    hausen
    0.10
    æľīå¤ļä¹Ī
    0.10
     sheer
    0.10
    å°Ĩæĺ¯
    0.10
    Activations Density 0.050%

    No Known Activations