© 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. 36621
    Prev
    Next
    INDEX
    Explanations

    reduce costs, turnover, stress, health

    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¿Ļå¥Ĺ
    -0.11
    æĥħåķĨ
    -0.09
    åĬ²
    -0.09
    å°½éĩı
    -0.09
    âĸ¾
    -0.09
    éĶĢåĶ®æ¸łéģĵ
    -0.09
    è¬Ŀ
    -0.09
    usk
    -0.09
     ÑħаÑĢакÑĤеÑĢиÑģÑĤ
    -0.09
    寮
    -0.08
    POSITIVE LOGITS
    åĴĮå®ĮåĸĦ
    0.08
    åIJİèĢħ
    0.08
     thiá»ĥu
    0.08
    (en
    0.08
    æŶéĹ´åĴĮ
    0.08
    mom
    0.08
    éĻĩ
    0.07
    باب
    0.07
    çķı
    0.07
    æľīåĬĽ
    0.07
    Activations Density 0.060%

    No Known Activations