© 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. 50345
    Prev
    Next
    INDEX
    Explanations

    ailments and symptoms

    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
    æĦ£
    -0.09
    cura
    -0.09
    åĴ§
    -0.09
    ä¾Ŀ次
    -0.09
    UST
    -0.08
    inson
    -0.08
    è¿Ļæł·ä¸Ģ个
    -0.08
    maf
    -0.08
    äºĭçī©
    -0.08
    åħ¨åĮº
    -0.08
    POSITIVE LOGITS
    å°±æĺ¯åĽłä¸º
    0.10
    çĽĬ
    0.09
    èĩªä»İ
    0.09
    å¯¹æľªæĿ¥
    0.09
    æ¯ĽçĹħ
    0.09
    (undefined
    0.09
    éļIJéļIJ
    0.09
    è°ĥçIJĨ
    0.09
    _due
    0.09
    Alternate
    0.09
    Activations Density 0.045%

    No Known Activations