© 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. 35812
    Prev
    Next
    INDEX
    Explanations

    python

    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
    iel
    -0.08
    наÑĤ
    -0.08
    ÑĤик
    -0.08
    ä¸ĸçķĮä¸Ģæµģ
    -0.08
    èººåľ¨
    -0.08
    éŁŃ
    -0.08
    综
    -0.08
    èµĸ
    -0.08
    fone
    -0.08
    à¸ģระà¸Ĺ
    -0.08
    POSITIVE LOGITS
    è¿Ļå¥Ĺ
    0.11
    èijĨ
    0.10
    ä¸Ľä¹¦
    0.10
    秦çļĩ
    0.10
    ä¸Ģå¥Ĺ
    0.10
    æ¢Ń
    0.09
    çıĬçijļ
    0.09
    举
    0.09
    æ¦ķ
    0.09
    èĵ¬
    0.09
    Activations Density 0.001%

    No Known Activations