© 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. 40124
    Prev
    Next
    INDEX
    Explanations

    prepositions before nouns

    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
    eting
    -0.09
    iland
    -0.08
    âĤĴ
    -0.08
     Prev
    -0.08
     reco
    -0.08
    æ¶Į
    -0.08
    éºĩ
    -0.07
    PASS
    -0.07
    趺
    -0.07
    dale
    -0.07
    POSITIVE LOGITS
    StateManager
    0.10
    åŁĴ
    0.10
    辨åĪ«
    0.09
    quist
    0.09
    åı£è¢ĭ
    0.09
    åľ¨éĩĮéĿ¢
    0.09
    æĢ¨
    0.09
    æ·
    0.09
    第ä¸Ģå±Ĭ
    0.09
    åĻ¶
    0.09
    Activations Density 0.177%

    No Known Activations