© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8106
    Prev
    Next
    INDEX
    Explanations

    achieve the same

    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
    人çĶŁçļĦ
    -0.09
     ÐĽÐµ
    -0.09
    ɥ
    -0.09
    渥
    -0.09
    éĿŀ常çļĦ
    -0.09
    гла
    -0.09
    çĶŁåij½çļĦ
    -0.09
    еÐ
    -0.09
    纸ä¸Ĭ
    -0.09
    ä¸ĸä¸Ĭ
    -0.09
    POSITIVE LOGITS
    åľ¨ç¾İåĽ½
    0.13
    åľ¨ä¸Ĭæµ·
    0.12
    èĢĮåľ¨
    0.12
    åľ¨æ·±åľ³
    0.12
    åľ¨æĹ¥æľ¬
    0.11
    åľ¨åĮĹ京
    0.11
    åľ¨é¦Ļ港
    0.11
     elsewhere
    0.10
    å·§
    0.10
    å¥¹åľ¨
    0.10
    Activations Density 0.813%

    No Known Activations