© 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. 47439
    Prev
    Next
    INDEX
    Explanations

    uncertainty

    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
    ends
    -0.09
     sorte
    -0.08
    rock
    -0.08
    аÑĨи
    -0.08
    olo
    -0.08
    å®ŀæĥł
    -0.07
    enco
    -0.07
    late
    -0.07
    allon
    -0.07
    èŃ·
    -0.07
    POSITIVE LOGITS
    ä¸įç¡®å®ļ
    0.11
    ingly
    0.11
    çªĺ
    0.11
    æĥ¶
    0.10
    å·²ä¹ħçļĦ
    0.10
    ertainty
    0.10
    ä¸įç¡®å®ļæĢ§
    0.10
    å°ĨæĿ¥
    0.10
    lli
    0.09
    åľ°è¯´
    0.09
    Activations Density 0.012%

    No Known Activations