© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37933
    Prev
    Next
    INDEX
    Explanations

    curious about

    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
    aque
    -0.10
    оказ
    -0.09
    tered
    -0.08
    aging
    -0.08
    uated
    -0.08
    czy
    -0.08
    æĢ»ä¹ĭ
    -0.08
    лов
    -0.08
    queued
    -0.08
    ISH
    -0.08
    POSITIVE LOGITS
    ä¸įå·²
    0.13
    å·²ä¹ħçļĦ
    0.12
    å·²ä¹ħ
    0.12
    åįģ足
    0.12
    ity
    0.11
    è¨ĢãģĪãģ°
    0.11
    è¿Ļæł·çļĦè¯Ŀ
    0.11
    èij©
    0.11
    çļĦçľ¼ç¥ŀ
    0.11
    -minded
    0.10
    Activations Density 0.006%

    No Known Activations