© 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. 38936
    Prev
    Next
    INDEX
    Explanations

    sounds too good to be true

    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
    åıªçŁ¥éģĵ
    -0.09
    baum
    -0.08
    memo
    -0.08
     Koh
    -0.08
    ìĨį
    -0.08
    еÑģÑģ
    -0.08
     dap
    -0.08
    åľ¨å¤ĸ
    -0.08
    ä¹ĭéģĵ
    -0.08
     APR
    -0.08
    POSITIVE LOGITS
    严èĤĥ
    0.14
    说ä¸įå®ļ
    0.11
    ç¡®
    0.11
    è¿ĺ羣
    0.10
     seriousness
    0.10
    å®ŀå®ŀåľ¨åľ¨
    0.10
    æŃ£è§Ħ
    0.09
    åĩłåĪĨ
    0.09
     legit
    0.09
    ereal
    0.09
    Activations Density 0.089%

    No Known Activations