© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21567
    Prev
    Next
    INDEX
    Explanations

    exprssing possession or past tense

    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
    å¤ĸç±į
    -0.10
     Scho
    -0.09
    IBUT
    -0.09
    é¾Ļæ¹ĸ
    -0.09
    æľīä¸įåIJĮçļĦ
    -0.08
    ä¹ĭæīĢ
    -0.08
    éļIJå½¢
    -0.08
    éķ
    -0.08
    å»ĵ
    -0.08
    æĤ¬æĮĤ
    -0.08
    POSITIVE LOGITS
    åĮĸè¿Ľç¨ĭ
    0.09
    æİı
    0.08
    åºĶæĶ¶
    0.08
    asher
    0.08
    åĨĻåĩº
    0.08
     Isl
    0.08
     ÑĥÑģп
    0.08
    æİıåĩº
    0.08
    éĢģåĩº
    0.08
    åħ³äºİæĪij们
    0.08
    Activations Density 0.024%

    No Known Activations