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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20729
    Prev
    Next
    INDEX
    Explanations

    here or there

    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
    è¿Ļæł·æīįèĥ½
    -0.11
    è¿Ļæł·çļĦè¯Ŀ
    -0.11
    è¿Ļæł·
    -0.10
    éĢĻ樣
    -0.10
    è¿Ļæł·åģļ
    -0.09
    æѤæŶ
    -0.09
    è¿Ļåħ¶ä¸Ń
    -0.09
    è¿Ļæĺ¯
    -0.09
     ÑįÑĤом
    -0.09
     hereby
    -0.09
    POSITIVE LOGITS
    åĨįåĪ°
    0.11
    æľĽåİ»
    0.10
    forth
    0.10
    é«ĺè´µ
    0.09
    æľīä»»ä½ķ
    0.09
    -addon
    0.08
    åı¤äºº
    0.08
    æİ¥åĪ°
    0.08
    ä¸Ģ个å¤ļ
    0.08
    ·»
    0.08
    Activations Density 0.010%

    No Known Activations