© 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. 52606
    Prev
    Next
    INDEX
    Explanations

    well tolerated

    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
    mue
    -0.10
    èĺ¼
    -0.09
    uze
    -0.08
    uyá»ĩn
    -0.08
    æ¡ĤèĬ±
    -0.08
    kaza
    -0.08
    cÃŃ
    -0.08
    esti
    -0.08
    mus
    -0.08
    orra
    -0.08
    POSITIVE LOGITS
    æİ¥åıĹ
    0.12
    æİ¥åıĹäºĨ
    0.12
    ament
    0.11
    æ±Łä¸ľ
    0.10
    èī¯å¥½
    0.10
    itivity
    0.10
    åıįåĵį
    0.10
    çıĤ
    0.10
    樽
    0.10
    è°ħ解
    0.09
    Activations Density 0.080%

    No Known Activations