© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 31807
    Prev
    Next
    INDEX
    Explanations

    campaigns and schools

    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
     blank
    -0.09
    以åħ¶
    -0.09
    à¸Ŀ
    -0.09
    è¸ıåħ¥
    -0.09
    æIJľ
    -0.09
    æ½
    -0.09
    æ··æ²Į
    -0.09
    交ä¼ļ
    -0.08
    æŃ»åIJİ
    -0.08
    èĩªä¸»çłĶåıij
    -0.08
    POSITIVE LOGITS
    å±ĭ顶
    0.09
    åīįç½®
    0.09
    é«ĺå³°æľŁ
    0.09
    äºİä¸Ģä½ĵ
    0.09
    eln
    0.09
    å§ĭ建
    0.08
    vox
    0.08
    建设åĴĮ
    0.08
    建设
    0.08
    cul
    0.08
    Activations Density 0.109%

    No Known Activations