© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 59247
    Prev
    Next
    INDEX
    Explanations

    pay / payment

    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
    Negative Logits
    .imp
    -0.10
    åİī
    -0.09
    èĬ±éĴ±
    -0.08
    èĺ¸
    -0.08
    èĨı
    -0.08
    eree
    -0.08
     Hoover
    -0.08
    å²ĺ
    -0.08
    éĻIJ
    -0.08
    èģĶ绾
    -0.08
    POSITIVE LOGITS
    鸬
    0.10
    æĸĩåĮĸ交æµģ
    0.09
    æĸĩåĮĸ产ä¸ļ
    0.09
    elight
    0.09
    翦
    0.09
    èĥ´
    0.09
    ä¼ļå±ķä¸Ńå¿ĥ
    0.09
    íķĺìĭ¤
    0.09
    交ç»Ļ
    0.09
    zu
    0.08
    Activations Density 0.026%

    No Known Activations