© 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. 49642
    Prev
    Next
    INDEX
    Explanations

    articles followed by specific nouns

    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
    åľ¨ç¾İåĽ½
    -0.10
    åľ¨æĪijåĽ½
    -0.09
    WithError
    -0.09
    åľ¨åħ¨çIJĥ
    -0.08
    è¯Ĭ
    -0.08
    大éģĵ
    -0.08
    åī¯æĢ»ç»ıçIJĨ
    -0.08
    çŃ¾è®¢äºĨ
    -0.08
    è¾IJ
    -0.08
    åľ¨ä¸ŃåĽ½
    -0.08
    POSITIVE LOGITS
    èĩªèº«
    0.09
    æľīåĪ©äºİ
    0.09
    -tm
    0.09
    orts
    0.09
    åħ³äºİ
    0.09
    è¿Ļæĸ¹éĿ¢
    0.09
    å®īåħ¨ä¿Ŀéļľ
    0.09
    æѦæŀĹ
    0.09
    åIJĮç±»
    0.09
    类似
    0.09
    Activations Density 0.412%

    No Known Activations