© 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. 38618
    Prev
    Next
    INDEX
    Explanations

    championships won

    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
    è·Łä¸įä¸Ĭ
    -0.11
    çľģåĨħ
    -0.10
    æľīä¸Ģå®ļ
    -0.09
    轶
    -0.09
    å½ĵåľ°
    -0.08
    à¸Ńม
    -0.08
    活泼
    -0.08
    èĸħ
    -0.08
    è¾Ł
    -0.08
    illery
    -0.08
    POSITIVE LOGITS
    æĺ¥æĻļ
    0.11
    çļĦä¼Łå¤§
    0.11
    å±Ī
    0.10
    奥è¿IJä¼ļ
    0.10
    å·ħå³°
    0.10
    åĿĿ
    0.09
    åĨ³èµĽ
    0.09
    æĢ»åĨ³èµĽ
    0.09
    宫殿
    0.09
    åı²è¯Ĺ
    0.09
    Activations Density 0.163%

    No Known Activations