© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37908
    Prev
    Next
    INDEX
    Explanations

    recently, until, now

    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¸Ģåľº
    -0.10
     веÑĩ
    -0.10
    ä¸Ģ份
    -0.10
    ä»ĸå·²ç»ı
    -0.09
    äºĨä¸Ģ份
    -0.09
    æ¿ł
    -0.09
    ä¸Ģç¢Ĺ
    -0.09
    éĹ³
    -0.09
    ä¸ĢæĿ¯
    -0.08
    à¹Ħว
    -0.08
    POSITIVE LOGITS
    çIJĨä¼ļ
    0.10
    åIJİæĿ¥
    0.09
    è¿ijäºĽå¹´
    0.09
    建ç«ĭåģ¥åħ¨
    0.09
    å¼ĢéĢļ
    0.09
    认æ¸ħ
    0.09
    ajar
    0.09
    å¼¼
    0.08
    kiem
    0.08
    à¸Ľà¸¥
    0.08
    Activations Density 0.041%

    No Known Activations