© 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. 3055
    Prev
    Next
    INDEX
    Explanations

    people and their contexts

    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
    ëĿ¼ëıĦ
    -0.09
     tapes
    -0.09
    çĤī
    -0.08
    prd
    -0.08
     Gos
    -0.08
    Outlet
    -0.08
    åĪĩæĸŃ
    -0.08
    çĶļèĩ³æĺ¯
    -0.08
    åľ°çIJĨ
    -0.08
    rand
    -0.07
    POSITIVE LOGITS
    é£İæݧ
    0.09
    éļĹ
    0.09
    æĬĺæī£
    0.09
    åıĭæĥħ
    0.09
    é£ŀæī¬
    0.08
    åĴĮæĬĢæľ¯
    0.08
    .solution
    0.08
    æŀģåĵģ
    0.08
    æ±¹
    0.08
    urf
    0.08
    Activations Density 0.051%

    No Known Activations