© 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. 56741
    Prev
    Next
    INDEX
    Explanations

    his followed by a possessive noun

    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¸ĢæĶ¯
    -0.12
    æĸ°ä¸ĸ纪
    -0.11
    ä¸Ģå¼Ģå§ĭå°±
    -0.11
    åIJĪéĢĤ
    -0.10
    ä¸Ģè¶Ł
    -0.10
    EMBER
    -0.10
    ä¸Ģæĸ¹éĿ¢
    -0.09
    åľ¨å®¶éĩĮ
    -0.09
    åĩºä¼ļ
    -0.09
    ä¸Ģ身
    -0.09
    POSITIVE LOGITS
    /her
    0.26
    sing
    0.17
    panic
    0.14
    zelf
    0.12
     own
    0.12
    æ±Ģ
    0.12
    /she
    0.11
    ä¿©
    0.11
     تعاÙĦÙī
    0.10
     Excell
    0.09
    Activations Density 0.086%

    No Known Activations