© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10266
    Prev
    Next
    INDEX
    Explanations

    attempting to do something

    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
    Not in Any Lists

    No Comments

    Negative Logits
    err
    -0.08
    å¾Ĺèµ·
    -0.08
     IMG
    -0.08
     err
    -0.08
    NgModule
    -0.07
    æĶ¿çŃĸæݪæĸ½
    -0.07
    Fit
    -0.07
     McM
    -0.07
    æİĽ
    -0.07
    éģ´éĢī
    -0.07
    POSITIVE LOGITS
    åºĸ
    0.10
    HITE
    0.10
    ächt
    0.09
    å¾ĹæĦı
    0.09
    解åĨ³éĹ®é¢ĺ
    0.09
    rvine
    0.09
    æ²IJæµ´
    0.09
    两ç§į
    0.08
    ç¦ı彩
    0.08
    .documentation
    0.08
    Activations Density 4.342%

    No Known Activations