© 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. 59063
    Prev
    Next
    INDEX
    Explanations

    Leia, Kent, Finnick

    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
    è¿ijè·Ŀ离
    -0.09
    åħ±åĴĮåĽ½
    -0.09
    auf
    -0.09
    çķĮ
    -0.09
    è·Łéļı
    -0.09
    aption
    -0.08
    ç»ķ
    -0.08
     lẫn
    -0.08
    èĤ¥
    -0.08
    egg
    -0.08
    POSITIVE LOGITS
    éĽªå±±
    0.11
    æĥľ
    0.10
    æĭŃ
    0.09
    缸åħ³ä¿¡æģ¯
    0.09
     lä
    0.09
    æĢľ
    0.09
    çĪº
    0.09
    .CommandType
    0.09
    è¿Ļ个人
    0.09
    .related
    0.09
    Activations Density 0.038%

    No Known Activations