© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 34381
    Prev
    Next
    INDEX
    Explanations

    contact information requests

    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
    æĶ¾æīĭ
    -0.10
    æݨå¼Ģ
    -0.10
    åı¬åĽŀ
    -0.10
    åİĮ
    -0.10
    æĴij
    -0.09
    ottes
    -0.09
    å½»
    -0.09
    .invoke
    -0.09
    åĩºåĽ½çķĻåѦ
    -0.09
    indexOf
    -0.09
    POSITIVE LOGITS
    ä¸įæŃ»
    0.09
    ç§ģ人
    0.09
    ç§ģãģĮ
    0.09
    絡
    0.09
    dong
    0.09
    æĪijæĬĬ
    0.09
    ç§ģ
    0.09
    ç»ı纪人
    0.09
    åįļ主
    0.09
    Private
    0.08
    Activations Density 0.029%

    No Known Activations