© 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. 21084
    Prev
    Next
    INDEX
    Explanations

    now if we

    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
    edly
    -0.09
    ä¾Ŀæīĺ
    -0.09
    å¹²èĦĨ
    -0.09
    æĪIJç«ĭ以æĿ¥
    -0.09
    éļĺ
    -0.09
    åľ¨åĵªéĩĮ
    -0.09
     Cohen
    -0.09
    ä»ĸå·²ç»ı
    -0.09
    çĺģ
    -0.09
    çŀŃ
    -0.08
    POSITIVE LOGITS
    osl
    0.10
    æīįæĺ¯
    0.09
    ModelProperty
    0.09
    WebRequest
    0.08
     chicago
    0.08
    лез
    0.08
    è«ĭ
    0.08
    AKE
    0.08
    vinc
    0.08
    亲
    0.08
    Activations Density 0.016%

    No Known Activations