© 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. 19365
    Prev
    Next
    INDEX
    Explanations

    on the

    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
    æݧèĤ¡éĽĨåĽ¢
    -0.10
    æĭIJ
    -0.09
    ovich
    -0.09
    æ¹ĸåĮº
    -0.09
    é¢ħ
    -0.09
    é³ĸ
    -0.08
    æ£ĭ
    -0.08
    ä¸Ńæľī
    -0.08
    åľ¨ä»Ĭå¹´
    -0.08
    зам
    -0.08
    POSITIVE LOGITS
    åħ¨é¢Ŀ
    0.09
    亲çĪ±
    0.09
    phalt
    0.09
    _hop
    0.09
    è¸ı
    0.08
    adies
    0.08
    说åĩº
    0.08
    åĭĩ
    0.08
     horm
    0.08
    太大
    0.08
    Activations Density 0.015%

    No Known Activations