© 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. 39182
    Prev
    Next
    INDEX
    Explanations

    wielding, juggling, aging

    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
     Weiss
    -0.09
    اض
    -0.09
    pled
    -0.08
    èĮ¸
    -0.08
    _consts
    -0.08
    hoot
    -0.08
    ÙĦÙħ
    -0.08
     изгоÑĤов
    -0.08
    æŀī
    -0.07
    رÙģ
    -0.07
    POSITIVE LOGITS
    NESS
    0.11
    çĿĢ
    0.10
    èĩªå¦Ĥ
    0.09
    忽
    0.09
    æĻºèĥ½æīĭæľº
    0.09
    å¾Ĺä½ı
    0.09
    able
    0.08
    亲
    0.08
    èµ·æĿ¥
    0.08
    èģĮæĿĥ
    0.08
    Activations Density 0.004%

    No Known Activations