© 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. 52797
    Prev
    Next
    INDEX
    Explanations

    years

    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
    åĪ©äºİ
    -0.09
    Ä°LÄ°
    -0.09
    angi
    -0.09
    aģı
    -0.09
    lica
    -0.09
    çijķ
    -0.09
    legg
    -0.08
    åĵĩ
    -0.08
    ÑģÑı
    -0.08
    нÑı
    -0.08
    POSITIVE LOGITS
    é¢ĩæľī
    0.08
     Henri
    0.08
    èĴ¯
    0.08
    大大å°ıå°ı
    0.08
    åıªä¸įè¿ĩæĺ¯
    0.08
    ãģĬãĤĬ
    0.08
    æĤ«
    0.08
    设ç«ĭäºĨ
    0.08
    æĪijè¿ĺ
    0.08
    ous
    0.08
    Activations Density 0.130%

    No Known Activations