© 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. 6074
    Prev
    Next
    INDEX
    Explanations

    ended [month/date] or as of [date]

    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
     tou
    -0.11
    åĨįéĢł
    -0.10
    cline
    -0.10
    ç°¸
    -0.09
     leaning
    -0.08
    çĺª
    -0.08
     Klein
    -0.08
    æĸ°ä¸ĸ纪
    -0.08
    PerPage
    -0.08
    çĸijéĹ®
    -0.08
    POSITIVE LOGITS
    èµĦäº§è´ŁåĢº
    0.13
    å¹´æľ«
    0.10
    æŃ¢
    0.10
    æľŁæľ«
    0.10
    æľĪæľ«
    0.10
    æĪªæŃ¢
    0.10
    (end
    0.09
    icz
    0.09
    åıĺå¾ĹæĽ´åĬł
    0.09
    ijd
    0.08
    Activations Density 0.032%

    No Known Activations