© 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. 59232
    Prev
    Next
    INDEX
    Explanations

    County name

    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
    ControlItem
    -0.09
    gee
    -0.08
    éİ®
    -0.08
    ÑĢо
    -0.08
    è¾ĥå°ı
    -0.08
    æĿ¥çļĦ
    -0.08
    avad
    -0.08
     klein
    -0.08
    phy
    -0.08
    å¼Ģè¾Ł
    -0.08
    POSITIVE LOGITS
     нем
    0.09
    åĽ½éĻħæľºåľº
    0.08
     moss
    0.08
    lip
    0.08
    æ±ŁåįĹ
    0.08
    èĬ±èįī
    0.08
    ï¸
    0.08
    åıįæŃ£
    0.08
     Zoo
    0.08
    rus
    0.08
    Activations Density 0.035%

    No Known Activations