© 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. 11029
    Prev
    Next
    INDEX
    Explanations

    never seen

    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¸Ģåij³
    -0.10
    ä¸ĢåĪĩ
    -0.08
    åIJĦæĸ¹
    -0.08
    ONO
    -0.08
    éĢģæĿ¥
    -0.08
    ä¸ĢåĪĩéĥ½
    -0.08
    éĢ¸
    -0.08
     Busy
    -0.08
    usher
    -0.08
    elper
    -0.08
    POSITIVE LOGITS
    ä»İæĿ¥æ²¡æľī
    0.14
    ä»İæĿ¥æ²¡
    0.11
    æľªæĽ¾
    0.11
    æŃ£å¼ı
    0.11
    ä»İæľª
    0.11
     EVER
    0.11
     ever
    0.10
    ç»ıåİĨè¿ĩ
    0.10
    éĻ¤æѤ
    0.10
    åIJ¬è¿ĩ
    0.10
    Activations Density 0.070%

    No Known Activations