© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 48934
    Prev
    Next
    INDEX
    Explanations

    develop standards

    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
    fos
    -0.10
     оÑĩеÑĢед
    -0.09
     оÑģÑĥÑīеÑģÑĤв
    -0.09
     ÑģовеÑĢÑĪ
    -0.09
    çİĭçīĮ
    -0.08
    éĺŁ
    -0.08
    ãĤ¹ãĤ¿ãĥĥãĥķ
    -0.08
    catch
    -0.08
    åŁİ乡
    -0.08
    车éĺŁ
    -0.08
    POSITIVE LOGITS
    æłĩåĩĨåĮĸ
    0.12
    èĩªå¾ĭ
    0.12
     industry
    0.11
    åIJĦ家
    0.11
    è¡Įä¸ļåįıä¼ļ
    0.11
     standards
    0.11
    ä¸ļçķĮ
    0.11
    èĩªæĦ¿
    0.11
    è¡Įä¸ļ
    0.10
    æłĩåĩĨ
    0.10
    Activations Density 0.115%

    No Known Activations