© 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. 35006
    Prev
    Next
    INDEX
    Explanations

    events and ceremonies

    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±ĬæŶ
    -0.10
    ä»ĸ们ä¼ļ
    -0.09
    ä»ĸä¼ļ
    -0.09
    åĪ°æŶåĢĻ
    -0.09
     СейÑĩаÑģ
    -0.09
    è¿Ļä¹Īå¤ļå¹´
    -0.09
    ä¹Łä¸įä¼ļ
    -0.09
    аеÑĤÑģÑı
    -0.09
    ä¸įä¼ļæľī
    -0.08
    ÑĩиÑĤÑĭва
    -0.08
    POSITIVE LOGITS
    举è¡ĮäºĨ
    0.14
    æĺ¨æĹ¥
    0.12
     yesterday
    0.12
    æĶ¶åĪ°äºĨ
    0.11
    Yesterday
    0.11
    åıĹåĪ°äºĨ
    0.11
    åľĨ满
    0.11
    æĺ¨å¤©
    0.11
    è§ģè¯ģäºĨ
    0.11
    åıĤåĬłäºĨ
    0.11
    Activations Density 0.229%

    No Known Activations