© 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. 3086
    Prev
    Next
    INDEX
    Explanations

    ski resorts and mountain locations

    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
    æ±Łæ·®
    -0.11
    æıª
    -0.10
    би
    -0.10
    æĤ²
    -0.09
    Lov
    -0.09
     Ard
    -0.08
     вÑĭÑĢажен
    -0.08
    Ụ
    -0.08
    çł£
    -0.08
     менее
    -0.08
    POSITIVE LOGITS
    é¤IJæ¡Į
    0.10
     Ranch
    0.09
    .rm
    0.09
    溷
    0.09
     Colorado
    0.09
    èĬ±å¼Ģ
    0.09
    è¿Ļå¼ł
    0.09
    ä¸Ģå¼ł
    0.09
     Idaho
    0.09
    ä»Ģä¹Īä¸ľè¥¿
    0.09
    Activations Density 0.149%

    No Known Activations