© 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. 29586
    Prev
    Next
    INDEX
    Explanations

    advertising, commercials, revenues

    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
    åĮª
    -0.09
    æŀ¢
    -0.09
    nic
    -0.09
    нал
    -0.09
     impro
    -0.09
    è¾¹éĻħ
    -0.08
     pint
    -0.08
    顽强
    -0.08
    éĶ¡
    -0.08
     pret
    -0.08
    POSITIVE LOGITS
    ords
    0.11
    elter
    0.10
    _ASCII
    0.08
    çłº
    0.08
    éŀį
    0.08
    cfg
    0.08
    纣
    0.08
    ãģ¤ãģį
    0.07
    æ¯Ĵ
    0.07
    åı¯è§Ĥ
    0.07
    Activations Density 0.016%

    No Known Activations