© 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. 50475
    Prev
    Next
    INDEX
    Explanations

    information provided or contained

    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°±çŁ¥éģĵ
    -0.08
    mani
    -0.08
    aring
    -0.08
    ãģĵãģĨ
    -0.08
    就没æľī
    -0.08
    å°±æĺ¯åľ¨
    -0.07
    以åıĬåħ¶ä»ĸ
    -0.07
    夫
    -0.07
    nie
    -0.07
    ÅĦst
    -0.07
    POSITIVE LOGITS
     mentioned
    0.10
    æīĢ示
    0.10
    æľ¬ç¶²ç«Ļ
    0.10
     previously
    0.09
     shown
    0.09
    eten
    0.09
     discussed
    0.09
    代表çĿĢ
    0.09
     ÑĢанее
    0.09
     listed
    0.09
    Activations Density 0.200%

    No Known Activations