© 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. 12409
    Prev
    Next
    INDEX
    Explanations

    preliminary followed by study or report

    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
    æıĨ
    -0.10
    uary
    -0.10
    éºĩ
    -0.09
     orm
    -0.09
    ortion
    -0.09
    busters
    -0.09
    alysis
    -0.09
    ification
    -0.09
    å¶Ļ
    -0.09
    ifice
    -0.09
    POSITIVE LOGITS
    mente
    0.10
    cial
    0.09
     ÑįÑĤап
    0.09
    iren
    0.09
    pton
    0.08
    antro
    0.08
    auge
    0.08
    ãĤģ
    0.08
    没æľīæĥ³åĪ°
    0.08
    haps
    0.08
    Activations Density 0.007%

    No Known Activations