© 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. 61991
    Prev
    Next
    INDEX
    Explanations

    of all sizes, types, ages

    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
    çī¹æľīçļĦ
    -0.10
    太å¤ļçļĦ
    -0.09
     ör
    -0.09
    å¾ĹäºĨ
    -0.09
    æľĢå¤ļçļĦ
    -0.09
    楼主
    -0.09
    æľĢå¤ļ
    -0.09
    ä½IJ
    -0.09
     Ñģвоего
    -0.09
    ä½ľé£İ
    -0.09
    POSITIVE LOGITS
    è°¶
    0.08
    ÙĦÙĩ
    0.08
    管çIJĨåĴĮ
    0.08
    orate
    0.08
    npc
    0.08
     Hut
    0.08
    çĭ¬è§Ĵåħ½
    0.08
    earer
    0.07
    _Min
    0.07
     Pell
    0.07
    Activations Density 0.033%

    No Known Activations