© 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. 9245
    Prev
    Next
    INDEX
    Explanations

    quantifiers or numbers

    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
    è¡Įãģį
    -0.11
    åı¦ä¸ĢåįĬ
    -0.10
    åħ¨äº§ä¸ļéĵ¾
    -0.10
    зад
    -0.09
     данном
    -0.09
    çļĦé£Łçī©
    -0.09
    äºĨè¿ĩæĿ¥
    -0.09
    æ²ī
    -0.09
    æľīè¿Ļæł·çļĦ
    -0.09
    _overflow
    -0.09
    POSITIVE LOGITS
    åĨħéĥ¨
    0.08
    羣æŃ£åģļåĪ°
    0.08
     internal
    0.08
     rounds
    0.08
     shades
    0.08
    agon
    0.08
     rer
    0.08
    aar
    0.08
    ä¸ĢäºĮ
    0.07
     Bol
    0.07
    Activations Density 0.153%

    No Known Activations