© 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. 951
    Prev
    Next
    INDEX
    Explanations

    emailing/emailed to someone

    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
    ä¸įäºĨ
    -0.11
    ivist
    -0.10
    ç½ijä¸Ĭ
    -0.10
    skirts
    -0.09
    mis
    -0.08
    tap
    -0.08
    ابر
    -0.08
     stalls
    -0.08
    宸
    -0.08
    orative
    -0.08
    POSITIVE LOGITS
     Ñģебе
    0.10
    ç»ĻåŃ©åŃIJ
    0.09
    ç»ĻåĪ«äºº
    0.09
    è¿ĩæĿ¥
    0.09
    ç»Ļä½łä»¬
    0.09
    éĥ¨åĪĨåĨħ容
    0.09
    èĦĨ
    0.09
    ç»Ļ人
    0.09
    å¼ĢæĿ¥
    0.08
    åıijçĶŁåıĺåĮĸ
    0.08
    Activations Density 0.022%

    No Known Activations