© 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. 29721
    Prev
    Next
    INDEX
    Explanations

    apostrophe s

    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
    iat
    -0.09
    êµIJ
    -0.09
     prospect
    -0.08
    è£Ĩ
    -0.08
    妨ç¢į
    -0.08
     Shine
    -0.08
    2
    -0.08
    0
    -0.08
     Feld
    -0.08
    heit
    -0.08
    POSITIVE LOGITS
    lessly
    0.11
    æŁIJç§į
    0.11
    ä»Ģä¹Īåľ°æĸ¹
    0.10
    éĹ´çļĦ
    0.09
    çļĦå¢ŀéķ¿
    0.09
    ippi
    0.09
    eworthy
    0.09
    argo
    0.09
    Ars
    0.09
    -trained
    0.09
    Activations Density 0.103%

    No Known Activations