© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20719
    Prev
    Next
    INDEX
    Explanations

    touch motion

    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
    è§ĦèĮĥ
    -0.08
    读æĩĤ
    -0.08
    大éĺŁ
    -0.08
    æ·±åĮĸæĶ¹éĿ©
    -0.08
    æī¹åĩĨ
    -0.08
    缩åĩı
    -0.08
    reau
    -0.08
     ephem
    -0.07
    å¼ĢéŨ
    -0.07
    çİ©ç¬ij
    -0.07
    POSITIVE LOGITS
    éļĭ
    0.12
    æľīæĽ´å¥½çļĦ
    0.10
     iOS
    0.10
    _IOS
    0.10
    -ios
    0.10
    æµ·æ£ł
    0.10
    .iOS
    0.10
    iOS
    0.09
    椰
    0.09
    _ios
    0.09
    Activations Density 0.196%

    No Known Activations