© 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. 37468
    Prev
    Next
    INDEX
    Explanations

    benefits, job, new, years

    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
    åŀĤ
    -0.08
    絡
    -0.08
    ÑĢоÑģÑģ
    -0.08
     bell
    -0.08
     COPYRIGHT
    -0.08
     TICK
    -0.08
    æķ°æį®åĪĨæŀIJ
    -0.08
    aphrag
    -0.08
    åģ¥
    -0.08
    tré
    -0.07
    POSITIVE LOGITS
    åīįæıIJæĺ¯
    0.10
    æľºåħ³
    0.10
    累积
    0.10
    åħ¨æĹ¥åĪ¶
    0.09
    ä¸į足
    0.09
    累计
    0.09
    å®īç½®
    0.09
    สะสม
    0.09
    溯
    0.09
    .builders
    0.09
    Activations Density 0.048%

    No Known Activations