© 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. 51528
    Prev
    Next
    INDEX
    Explanations

    federal law regulations directives

    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
    士
    -0.11
    è¯ģ
    -0.09
    starter
    -0.08
    é²µ
    -0.08
    åĬŁå¤«
    -0.08
    ensively
    -0.08
    stant
    -0.07
    ç¨
    -0.07
    éĹ»
    -0.07
    toa
    -0.07
    POSITIVE LOGITS
    ç»ıéªĮåĴĮ
    0.10
    æı®
    0.10
    å«ī
    0.09
    éĥ¨å§Ķ
    0.09
    人ãģ¨
    0.09
    ÑİÑīие
    0.09
    æĮijåīĶ
    0.09
    ç²¾ç¥ŀ
    0.09
    ROL
    0.09
    åĴĮåľ°åĮº
    0.09
    Activations Density 0.133%

    No Known Activations