© 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. 60568
    Prev
    Next
    INDEX
    Explanations

    any variation

    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
    imas
    -0.09
    riter
    -0.08
     Polar
    -0.08
    _INST
    -0.08
    mailto
    -0.08
    chers
    -0.08
    opard
    -0.08
     carniv
    -0.08
    EG
    -0.07
    ry
    -0.07
    POSITIVE LOGITS
    çĬĬ
    0.10
    åĴĮåľ°åĮº
    0.10
    æ´»çĿĢ
    0.10
    æĪ¢
    0.09
    饿
    0.09
    æ¹Ħ
    0.09
     umie
    0.09
    åģĩåĨĴ
    0.09
    åĴİ
    0.09
    丰满
    0.09
    Activations Density 0.035%

    No Known Activations