© 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. 34258
    Prev
    Next
    INDEX
    Explanations

    in combination with

    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
    omer
    -0.11
    åĽłä¸ºåľ¨
    -0.10
    /is
    -0.10
    oretical
    -0.09
    ç«¥
    -0.09
    ä¸įäºĨ
    -0.09
    ucks
    -0.09
    oba
    -0.09
    _VE
    -0.09
    庶
    -0.09
    POSITIVE LOGITS
    çĶ¨å¾®ä¿¡
    0.09
    çļĦæĸ¹å¼ı
    0.08
    çļĦä¸ĢäºĽ
    0.08
    fax
    0.08
    ä¸ĢåŃ£åº¦
    0.08
    èĦIJ
    0.08
    娲
    0.08
    æĸ°ä¸ŃåĽ½
    0.08
    ä¸ĢåıĮ
    0.08
    æĹ¶ä»£ä¸ŃåĽ½
    0.08
    Activations Density 0.348%

    No Known Activations