© 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. 12430
    Prev
    Next
    INDEX
    Explanations

    rows in dataframes and tables

    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
    	TokenName
    -0.10
    odem
    -0.10
    adir
    -0.09
    جاز
    -0.09
    ÑĤÑĮ
    -0.08
    دا
    -0.08
    ëį°
    -0.08
    loo
    -0.08
    æ°Ľ
    -0.08
    çĸĻ
    -0.08
    POSITIVE LOGITS
    boat
    0.13
    ever
    0.13
    dfunding
    0.11
    itz
    0.10
    orld
    0.10
    åĵº
    0.10
    ãģ¹ãģį
    0.10
    ignon
    0.09
    ings
    0.09
    anna
    0.09
    Activations Density 0.055%

    No Known Activations