© 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. 24004
    Prev
    Next
    INDEX
    Explanations

    Pagoda

    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
    OfDay
    -0.09
    specs
    -0.09
    око
    -0.08
    缮æłĩ
    -0.08
     ÑĤеÑħнологии
    -0.08
     dung
    -0.08
    arter
    -0.08
    ä¸Ģä½ĵ
    -0.08
    æĤ£
    -0.08
    çĽ
    -0.08
    POSITIVE LOGITS
    éŁŃ
    0.10
    ish
    0.10
    IZER
    0.10
    letic
    0.09
    æĶ¥
    0.09
    ité
    0.09
    ÑĪин
    0.09
    åĬłçıŃ
    0.09
    åĬ©çIJĨ
    0.08
    éĢĨè¡Į
    0.08
    Activations Density 0.007%

    No Known Activations