© 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. 6860
    Prev
    Next
    INDEX
    Explanations

    email or mail communication

    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
    åĮ¡
    -0.09
     гоÑģÑĥдаÑĢ
    -0.09
    碲
    -0.08
    ä¸įçĽ¸ä¿¡
    -0.08
    enance
    -0.08
     оÑĤно
    -0.08
    åĨ³è®®
    -0.08
     monopol
    -0.08
    ç«Ł
    -0.08
    çī¹åĪ«å£°æĺİ
    -0.08
    POSITIVE LOGITS
    åIJĦä½į
    0.09
    æ¯ıä½į
    0.09
     duck
    0.09
    ripp
    0.09
    åĬ¨å·¥
    0.09
    duck
    0.09
    çĿ£
    0.08
    ê°ģ
    0.08
    åIJĦ
    0.08
    å¨ĥ
    0.08
    Activations Density 0.029%

    No Known Activations