© 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. 47574
    Prev
    Next
    INDEX
    Explanations

    rescue and operations

    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
     SALE
    -0.10
    èĿī
    -0.09
    ç²¾èĩ´
    -0.09
    AtPath
    -0.09
    æĬµåĪ¶
    -0.09
    è´¨
    -0.09
     minib
    -0.08
    สà¸ĩà¸Ħราม
    -0.08
    ä¸įåİ»
    -0.08
     оÑĤкÑĢÑĭва
    -0.08
    POSITIVE LOGITS
    æIJľæķij
    0.15
    è¢«åĽ°
    0.13
    æķijåĬ©
    0.13
    æķij人
    0.13
    缴åįĩæľº
    0.11
    æķij
    0.10
    æķijæı´
    0.10
     resc
    0.10
    æĬ¢æķij
    0.10
    çĶ³
    0.10
    Activations Density 0.037%

    No Known Activations