© 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. 24054
    Prev
    Next
    INDEX
    Explanations

    desired outcome

    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
    åģļèµ·
    -0.10
    RGBO
    -0.10
    uess
    -0.09
    elige
    -0.09
    è§ij
    -0.09
    æ¯ķç«Łæĺ¯
    -0.09
    æľªçŁ¥
    -0.09
    ROY
    -0.09
    ç§ijæķĻ
    -0.08
     POSS
    -0.08
    POSITIVE LOGITS
     desired
    0.20
    desired
    0.16
     Desired
    0.13
     desire
    0.12
    æīĢéľĢçļĦ
    0.11
    满æĦıçļĦ
    0.10
     desirable
    0.10
    æīĢéľĢ
    0.10
     wanted
    0.10
     desires
    0.09
    Activations Density 0.118%

    No Known Activations