© 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. 26721
    Prev
    Next
    INDEX
    Explanations

    added value, VAT

    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
     Huff
    -0.09
    è¥Ł
    -0.09
    æĬľ
    -0.09
    浩
    -0.09
    æģ©æĸ½
    -0.09
    CharacterSet
    -0.09
    è¾¾å°Ķ
    -0.09
    ollow
    -0.08
    å¥
    -0.08
    æŀ¸
    -0.08
    POSITIVE LOGITS
    å¢ŀåĢ¼æľįåĬ¡
    0.10
    å¢ŀåĢ¼
    0.10
    -added
    0.10
    Cog
    0.10
    æĺĤè´µ
    0.09
    èıľ
    0.09
    饽
    0.09
    æľįåĬ¡ä¸Ńå¿ĥ
    0.08
    æ¯ģçģŃ
    0.08
    ÑĭÑĪ
    0.08
    Activations Density 0.015%

    No Known Activations