© 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. 9236
    Prev
    Next
    INDEX
    Explanations

    all 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
    åĻ©
    -0.09
    ä¸Ģç»Ħ
    -0.09
    ä¸ĭä¸Ģ个
    -0.09
    ilo
    -0.09
    овой
    -0.09
    ìĤ¬ìĿ´
    -0.09
    овÑĭм
    -0.09
    ä¸ĩä¸Ģ
    -0.09
    ä¸įç»ı
    -0.09
    æŶè£ħ
    -0.09
    POSITIVE LOGITS
    addock
    0.09
    åħ¨é¢Ŀ
    0.08
    åĵĦ
    0.08
    æľªæĪIJ
    0.08
    ä¼ı
    0.07
    æĦĨ
    0.07
    abra
    0.07
    1
    0.07
    gos
    0.07
    åıĮåıĮ
    0.07
    Activations Density 0.090%

    No Known Activations