© 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. 32850
    Prev
    Next
    INDEX
    Explanations

    IS NOT

    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
    ä¸Ģåıª
    -0.10
    æ°¸ä¹ħ
    -0.08
    å¤ĦåĪĨ
    -0.08
    èįīåľ°
    -0.08
    ndx
    -0.08
    å¥ĩå¦Ļ
    -0.08
    ä½łçŁ¥éģĵ
    -0.08
    éĨĴ
    -0.08
     toughest
    -0.08
    æĸ°å¨ĺ
    -0.08
    POSITIVE LOGITS
    æĪĸå¤ļ
    0.09
     заÑĤ
    0.08
     jus
    0.08
    ä¸įçĦ¶
    0.08
     Tut
    0.08
    Frozen
    0.08
    bjerg
    0.08
    urrenc
    0.08
     shutter
    0.08
    ibil
    0.08
    Activations Density 0.145%

    No Known Activations