© 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. 63825
    Prev
    Next
    INDEX
    Explanations

    publishing houses

    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
    ä¹ĥ
    -0.10
    åĩł
    -0.08
    ç¯Ĩ
    -0.08
    æľįåĬ¡ä½ĵç³»
    -0.08
    æѤæĸĩ
    -0.08
    åľ¨å¹¿å·ŀ
    -0.08
     Linkedin
    -0.08
    bitset
    -0.08
    èĦı
    -0.08
    åľ¨æ·±åľ³
    -0.08
    POSITIVE LOGITS
    åıijè¡Į
    0.10
    обÑĢаж
    0.08
    adays
    0.08
     mũi
    0.08
    unting
    0.08
     Hutchinson
    0.08
    ç¹ģ
    0.08
    ierung
    0.08
    alcon
    0.08
    .arrow
    0.08
    Activations Density 0.051%

    No Known Activations