© 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. 37106
    Prev
    Next
    INDEX
    Explanations

    The Radical Squadron characters

    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
     оÑĤд
    -0.09
     اÙĦتج
    -0.09
    åIJĦéĥ¨éŨ
    -0.09
    sti
    -0.09
     ÑĢÑĥковод
    -0.08
     cann
    -0.08
    æĮĩå°İ
    -0.08
     дог
    -0.08
    æĮĩ导
    -0.08
    ollo
    -0.08
    POSITIVE LOGITS
    梳
    0.10
    æĪ®
    0.09
    ỵ
    0.09
    羣åģĩ
    0.09
    æ¨ĺ
    0.09
    inka
    0.09
    åģı好
    0.08
    åįļ彩
    0.08
     enqu
    0.08
    è´¨éĩıå®īåħ¨
    0.08
    Activations Density 0.023%

    No Known Activations