© 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. 35624
    Prev
    Next
    INDEX
    Explanations

    new [noun]

    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
    对æİ¥
    -0.10
    èĵ¬
    -0.08
    ä¹Łä¸įéĶĻ
    -0.08
    ãĤīãģĦ
    -0.08
    å¢ŀå¹ħ
    -0.08
    æŀģåĬĽ
    -0.08
    åIJĮæĥħ
    -0.08
    ä¸Ģå®ļ
    -0.08
    1
    -0.08
    åĪ°åºķæĺ¯
    -0.08
    POSITIVE LOGITS
    iator
    0.12
    æĹ¶ä»£çļĦ
    0.10
    iates
    0.10
     kind
    0.09
    âĪŁ
    0.09
    è¯ģçĽij
    0.09
    обÑĢаз
    0.09
     khảo
    0.09
    éĿĴæĺ¥
    0.09
    æĺİæĹ¥
    0.09
    Activations Density 0.049%

    No Known Activations