© 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. 59109
    Prev
    Next
    INDEX
    Explanations

    heritage sites and preservation

    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
    AILS
    -0.10
    æĪijå¸ĮæľĽ
    -0.10
    зд
    -0.09
    æ±īåŃIJ
    -0.09
     новоÑģÑĤи
    -0.09
    éĤ
    -0.09
    è¿Ļ家ä¼Ļ
    -0.09
    æijĶåĢĴ
    -0.09
    å°±è¿ij
    -0.09
    .KEY
    -0.09
    POSITIVE LOGITS
     UNESCO
    0.12
    ugh
    0.09
    pid
    0.09
    çĶ³æĬ¥
    0.09
    仲
    0.09
     pil
    0.09
     syncing
    0.08
    åıĮéĩį
    0.08
     Expl
    0.08
     Barcode
    0.08
    Activations Density 0.041%

    No Known Activations