© 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. 38815
    Prev
    Next
    INDEX
    Explanations

    оÑĤкÑĢÑĭ

    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
    ģ
    -0.09
    åĽŀ头
    -0.09
    atic
    -0.09
    åĨ¬åŃ£
    -0.09
    aus
    -0.09
    讲课
    -0.08
    fully
    -0.08
    clist
    -0.08
    åĽłä¸ºæĪij
    -0.08
     formas
    -0.08
    POSITIVE LOGITS
    делÑĮ
    0.12
    åĽ¢éķ¿
    0.10
    æĸ°åĬłåĿ¡
    0.10
    ç¿ħ
    0.10
    меÑĩа
    0.09
    обÑĢаж
    0.09
    Ñij
    0.09
    iable
    0.09
    кÑĢÑĭ
    0.09
    кÑĢо
    0.09
    Activations Density 0.013%

    No Known Activations