© 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. 8858
    Prev
    Next
    INDEX
    Explanations

    breakout word

    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
     Vance
    -0.09
    ifu
    -0.09
    彩
    -0.08
    èĬĿ
    -0.08
    stand
    -0.08
    æ§İ
    -0.08
    ably
    -0.08
    èªĵè¨Ģ
    -0.08
    æĦı大
    -0.08
     Arabs
    -0.08
    POSITIVE LOGITS
    çĬį
    0.09
    æµģè¡ĮçļĦ
    0.09
    scopes
    0.09
    ä¸Ģæĸ¹
    0.09
    å¹ķåIJİ
    0.09
    ä¸ĢéŨ
    0.09
    èĢĮåĩº
    0.09
    ãĤ»ãĥ³
    0.09
    æĸ°çļĦä¸Ģå¹´
    0.09
    spread
    0.09
    Activations Density 0.007%

    No Known Activations