© 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. 8979
    Prev
    Next
    INDEX
    Explanations

    downloadable product/pack

    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
    èĪĽ
    -0.08
    æĭIJ
    -0.08
    ä¿IJ
    -0.08
    precision
    -0.08
    sla
    -0.08
    elon
    -0.08
    建çŃijæĿIJæĸĻ
    -0.08
    ALER
    -0.08
    intros
    -0.07
    èĢģçĻ¾å§ĵ
    -0.07
    POSITIVE LOGITS
    одеÑĢж
    0.10
    ç´łæĿIJ
    0.10
    ä½ľåĵģåĨħ容
    0.09
    æĬ½
    0.09
    ç»Ī身
    0.09
    åĮħåIJ«
    0.09
    买家
    0.09
    èIJĿ
    0.08
     Etsy
    0.08
     purchaser
    0.08
    Activations Density 0.057%

    No Known Activations