© 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. 30030
    Prev
    Next
    INDEX
    Explanations

    past tense verbs

    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
    è¿Ļéĥ¨åĪĨ
    -0.10
    æľī两ç§į
    -0.09
    ä¸Ģéĥ¨åĪĨ
    -0.09
    è¿Ļæī¹
    -0.08
    è¿Ļäºĭ
    -0.08
     Rare
    -0.08
    ä½ľèĢħæľ¬äºº
    -0.08
    _literal
    -0.08
    åı¦ä¸Ģç§į
    -0.08
    æ»ĺ
    -0.08
    POSITIVE LOGITS
    éĢĶ
    0.09
    åĿļæĮģ以
    0.09
    ehr
    0.09
    ä¸įåIJĮç¨ĭ度
    0.09
    CLUSIVE
    0.09
    åĬłæĭ¿
    0.09
    eh
    0.09
    ë´ī
    0.08
    好è¿IJ
    0.08
    amon
    0.08
    Activations Density 0.228%

    No Known Activations