© 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. 54387
    Prev
    Next
    INDEX
    Explanations

    intellectual property secrets

    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
    çĸ¯
    -0.10
    è¶ĬæĿ¥è¶Ĭ大
    -0.10
    驯
    -0.10
    èĥ¡åIJĮ
    -0.09
    æĮĤçīĮ
    -0.09
    è£ĺ
    -0.09
    ptions
    -0.09
    æ¯Ĵ
    -0.09
    涨
    -0.09
    ä¸Ńæĸ°
    -0.09
    POSITIVE LOGITS
    ä¿Ŀå¯Ĩ
    0.18
     proprietary
    0.15
    çļĦç§ĺå¯Ĩ
    0.15
    ç§ĺ
    0.14
    ç§ĺå¯Ĩ
    0.14
    ç¥ŀç§ĺ
    0.13
    secret
    0.12
     secret
    0.12
     Confidential
    0.12
    ç¥ķ
    0.11
    Activations Density 0.153%

    No Known Activations