© 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. 29519
    Prev
    Next
    INDEX
    Explanations

    French art schools

    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
     Helm
    -0.09
    å®Ľå¦Ĥ
    -0.08
    Deal
    -0.08
    çݰ身
    -0.08
    èĮ¹
    -0.08
    çĸı导
    -0.08
    лей
    -0.08
    chem
    -0.08
    .emp
    -0.08
    ç¯ĩç«ł
    -0.07
    POSITIVE LOGITS
    ç¾İæľ¯
    0.16
    èīºæľ¯
    0.13
    ç»ĺçĶ»
    0.13
    审ç¾İ
    0.12
    éĢłåŀĭ
    0.12
     диз
    0.12
    ãĥĩãĤ¶ãĤ¤ãĥ³
    0.12
    æĸĩåĮĸèīºæľ¯
    0.11
    èī²å½©
    0.11
    çĶ»çĶ»
    0.11
    Activations Density 0.132%

    No Known Activations