© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 32732
    Prev
    Next
    INDEX
    Explanations

    determiners followed by 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
    ä»Ģä¹Īéĥ½
    -0.09
    éĢıæ°Ķ
    -0.09
    æ§Ľ
    -0.09
    ç§īæĮģ
    -0.09
    ä»Ģä¹Īåij¢
    -0.09
    åľ¨ä»Ĭå¹´
    -0.08
    æ°Ķåij³
    -0.08
    温馨
    -0.08
    ä¸Ĭåīį
    -0.08
    åĹħ
    -0.08
    POSITIVE LOGITS
    æѤåĪ»
    0.09
    诱人
    0.08
    uck
    0.08
    éĥ¨ä»½
    0.08
    æĦļ
    0.08
    upt
    0.08
    æīĢåľ¨
    0.08
    illon
    0.08
    endor
    0.07
    nin
    0.07
    Activations Density 0.107%

    No Known Activations