© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 12378
    Prev
    Next
    INDEX
    Explanations

    inspiring and inspirational words

    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
    Negative Logits
    èĮ§
    -0.11
    åĬłå¼ºå¯¹
    -0.09
    åĢı
    -0.08
    .sav
    -0.08
    ä»ĺåĩº
    -0.08
     raging
    -0.08
    vy
    -0.08
    اض
    -0.08
    åĨ·åĨ·
    -0.08
    éľĵ
    -0.08
    POSITIVE LOGITS
    é¼ĵèĪŀ
    0.11
    åIJ¯åıij
    0.11
     inspire
    0.10
     awe
    0.10
    æľªæĿ¥åıijå±ķ
    0.10
    羡
    0.10
    æ¿ĢåĬ±
    0.10
     дÑĥÑħ
    0.09
    人å¿ĥ
    0.09
    åĴ¤
    0.09
    Activations Density 0.018%

    No Known Activations