© 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. 20036
    Prev
    Next
    INDEX
    Explanations

    URLs and web links

    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
    ç³Ł
    -0.09
    楽ãģĹãģ¿
    -0.09
    RIX
    -0.08
    ä½Ĩ对äºİ
    -0.08
    çŃīåĪ°
    -0.08
     Spicer
    -0.08
    è¿Ļ段
    -0.08
    ç»ĻåĪ«äºº
    -0.08
    elan
    -0.08
    ä½ľä¸ºä¸ĢåIJį
    -0.08
    POSITIVE LOGITS
    çĶµè¯Ŀ
    0.10
    ä¼ļè®©ä½ł
    0.09
    =http
    0.08
    ÑĩнаÑı
    0.08
    建çŃijæĿIJæĸĻ
    0.08
    é¢ľ
    0.08
     Mess
    0.08
    äºķ
    0.08
    åĩ¡æĺ¯
    0.08
    å¡ij
    0.08
    Activations Density 0.029%

    No Known Activations