© 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. 9150
    Prev
    Next
    INDEX
    Explanations

    weather forecasts

    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
    ansi
    -0.09
    Ãłng
    -0.08
    blind
    -0.08
    alem
    -0.08
    ationToken
    -0.08
    åIJįè¯į
    -0.08
     Ler
    -0.08
     Pascal
    -0.08
    éĩĬ
    -0.08
    REDIS
    -0.08
    POSITIVE LOGITS
    ä»Ĭ
    0.10
    åĽŀåij³
    0.10
    ä»ĬæĹ¥
    0.09
    rary
    0.09
    ç»į
    0.09
    unes
    0.09
    ä¿¡æģ¯æľįåĬ¡
    0.09
    ä¸ĢåĪĻ
    0.09
    æĮĩ导
    0.08
     cục
    0.08
    Activations Density 0.016%

    No Known Activations