© 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. 26260
    Prev
    Next
    INDEX
    Explanations

    doubles or singles

    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
     trib
    -0.09
    ware
    -0.09
     Trib
    -0.08
    éĴī
    -0.08
    asl
    -0.08
    ynthesis
    -0.08
    åĵģä½į
    -0.08
    Ware
    -0.08
    读èĢħ
    -0.08
    itches
    -0.07
    POSITIVE LOGITS
    åıĮåıĮ
    0.11
    稷
    0.10
    åıĮ
    0.10
    æIJŃæ¡£
    0.10
     Masc
    0.10
    éĽĻ
    0.10
    joint
    0.10
    鸳
    0.10
    åĽ¢éĺŁ
    0.10
    éĺ´éĺ³
    0.09
    Activations Density 0.105%

    No Known Activations