© 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. 51493
    Prev
    Next
    INDEX
    Explanations

    account security

    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
    å·¡åĽŀ
    -0.10
    PRICE
    -0.09
    è°±
    -0.09
    æĢ»ä»·
    -0.09
    åĽ«
    -0.09
    åįķä»·
    -0.09
    åİŁåŀĭ
    -0.08
    群ä½ĵ
    -0.08
     PRICE
    -0.08
     ×ŀ×Ĺ×Ļר
    -0.08
    POSITIVE LOGITS
    å¹³åı°ä¸Ĭ
    0.11
    å¹³åı°
    0.10
    æıIJçİ°
    0.10
    (platform
    0.10
    éĩįéĩijå±ŀ
    0.09
    çļĦ身份
    0.09
    累计
    0.09
    æ°´æĻ¶
    0.09
     platform
    0.09
    æģ¢å¤įæŃ£å¸¸
    0.09
    Activations Density 0.062%

    No Known Activations