© 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. 49457
    Prev
    Next
    INDEX
    Explanations

    turns out that

    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
    æľīä¿¡å¿ĥ
    -0.10
    ä¸Ģå®ļä¼ļ
    -0.10
    åı¯æĥ³
    -0.10
    OUN
    -0.09
    æ¯Ķè¾ĥå¤ļ
    -0.09
    èĤ¯å®ļä¼ļ
    -0.09
    ssi
    -0.09
    æ³ķå¾ĭ顾éĹ®
    -0.09
    å¿Ĵ
    -0.09
    гÑĢан
    -0.09
    POSITIVE LOGITS
    ç«Łæĺ¯
    0.13
    åİŁæĿ¥
    0.11
    åİŁä¾Ĩ
    0.10
    ç«ŁçĦ¶
    0.09
    arently
    0.09
    çĦ¶æĺ¯
    0.09
    å·§åIJĪ
    0.09
    çģ«çĥ§
    0.09
    ç¢ĺ
    0.09
     Dodge
    0.09
    Activations Density 0.019%

    No Known Activations