© 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. 16675
    Prev
    Next
    INDEX
    Explanations

    high quality products

    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
    åĩłç§į
    -0.10
    åı¯è§Ĥ
    -0.09
    个人
    -0.09
     Imper
    -0.09
    éĥ¨åĪĨ
    -0.08
    coop
    -0.08
    åĬ¨åĬĽ
    -0.08
    çĶļèĩ³
    -0.08
    mani
    -0.08
    .disk
    -0.08
    POSITIVE LOGITS
    ä¸įæĸŃåĪĽæĸ°
    0.10
    inn
    0.10
    è¡ħ
    0.10
    ä¼ĺè´¨
    0.09
    èĤ¡æľ¬
    0.09
    æĬĢæľ¯åĪĽæĸ°
    0.09
    é¢ĨåħĪçļĦ
    0.09
    é«ĺåĵģè´¨
    0.09
    cla
    0.09
    ä¼ĺè´¨çļĦ
    0.09
    Activations Density 0.084%

    No Known Activations