© 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. 63679
    Prev
    Next
    INDEX
    Explanations

    server configuration changes

    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
    æ³
    -0.10
     Hiring
    -0.09
    ä¸ĥæĺŁ
    -0.09
    iaux
    -0.09
    æµģæ°´
    -0.09
    æĭĽèģĺ
    -0.09
    çī¹èī²äº§ä¸ļ
    -0.09
    èĩªå¸¦
    -0.08
    èĩªåĬ©
    -0.08
    .StackTrace
    -0.08
    POSITIVE LOGITS
    容éĩı
    0.09
    好äºĨ
    0.09
    çݯå¢ĥä¸Ń
    0.09
    éķĵ
    0.09
     Mosque
    0.08
    ÙĦاÙħ
    0.08
    ylan
    0.08
     GRAT
    0.08
     TZ
    0.08
    åļ´
    0.08
    Activations Density 0.146%

    No Known Activations