© 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. 3111
    Prev
    Next
    INDEX
    Explanations

    references and terms

    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
    Not in Any Lists

    No Comments

    Negative Logits
    åŃļ
    -0.09
    asco
    -0.09
    chas
    -0.09
     Incre
    -0.09
    åĶ¿
    -0.09
    湫
    -0.09
    çĤ¹åĩ»æŁ¥çľĭ
    -0.09
    èµĢ
    -0.09
    -volume
    -0.08
    ç®ķ
    -0.08
    POSITIVE LOGITS
    rops
    0.09
    _hop
    0.08
    nard
    0.07
    æĶ¿çŃĸæݪæĸ½
    0.07
    æĪIJç«ĭäºĨ
    0.07
    åĪĿåĪĽ
    0.07
    rl
    0.07
    uner
    0.07
    æĹĹ
    0.07
    ä¹ĥ
    0.07
    Activations Density 0.001%

    No Known Activations