© 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. 32261
    Prev
    Next
    INDEX
    Explanations

    water and atmosphere

    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
    æĭīæĸ¯
    -0.10
    åĩºåıij
    -0.09
    çĿĢçľ¼äºİ
    -0.09
    ãģ¤ãģį
    -0.09
    çĿĢçľ¼
    -0.09
    æīįåı¯ä»¥
    -0.09
    æµ¦ä¸ľ
    -0.08
    è¿Ļç§į
    -0.08
    ستاÙĨ
    -0.08
    æĿ³
    -0.08
    POSITIVE LOGITS
    ä¸ĭä¸Ģ代
    0.11
     unsus
    0.09
    é¤IJæ¡Į
    0.09
    _sensitive
    0.08
    è¿ĽèĢĮ
    0.08
    çļĦåı¯èĥ½æĢ§
    0.08
    èĶĵ延
    0.08
    ä¹ĥèĩ³
    0.08
    åIJİç»Ń
    0.08
    éĿ¢åīį
    0.08
    Activations Density 0.138%

    No Known Activations