© 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. 56198
    Prev
    Next
    INDEX
    Explanations

    help you

    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
    нÑĮ
    -0.09
     Pix
    -0.09
    quito
    -0.08
    uspended
    -0.08
    çĪ±åĽ½ä¸»ä¹ī
    -0.08
    nings
    -0.08
    rogen
    -0.08
     пÑĢог
    -0.08
    ucer
    -0.08
     Kendrick
    -0.08
    POSITIVE LOGITS
    è¿ĻäºĽéĹ®é¢ĺ
    0.14
    åľ¨è¿Ļæĸ¹éĿ¢
    0.13
    ä¸įä½Ĩ
    0.13
    è¿Ļ个éĹ®é¢ĺ
    0.12
    è¿Ļç§įæĥħåĨµ
    0.12
    对æѤ
    0.12
    æģ°æģ°
    0.11
    è¿Ļä¸ĢåĪĩ
    0.11
    èĦ±é¢ĸèĢĮåĩº
    0.10
    è¿Ļæĸ¹éĿ¢
    0.10
    Activations Density 0.226%

    No Known Activations