© 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. 16649
    Prev
    Next
    INDEX
    Explanations

    merchantability or fitness

    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
    perial
    -0.10
    夺
    -0.09
    alie
    -0.09
    æľį
    -0.09
    agged
    -0.09
    ype
    -0.09
    樽
    -0.09
    adol
    -0.09
     Aunt
    -0.09
     Burk
    -0.08
    POSITIVE LOGITS
    REM
    0.10
    æµģéĢĿ
    0.09
    è¯Ħè®®
    0.09
    icum
    0.09
    ä¿¡èµĸ
    0.09
    lm
    0.08
    书éĻ¢
    0.08
    è·º
    0.08
    å±ħ室
    0.08
     rum
    0.08
    Activations Density 0.008%

    No Known Activations