© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51955
    Prev
    Next
    INDEX
    Explanations

    explaining or describing something

    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
     Nunes
    -0.10
    线索
    -0.09
     lect
    -0.09
    lect
    -0.08
    åłª
    -0.08
    ogie
    -0.08
    åijĬ
    -0.08
    æ´¥
    -0.08
    讲课
    -0.08
    à¹Ģà¸ķ
    -0.07
    POSITIVE LOGITS
    éĤ£ç§į
    0.11
    éĤ£æ®µ
    0.10
    iates
    0.10
    è¿Ļ两天
    0.10
    ozo
    0.10
    åıįæŃ£
    0.10
    æ·¹
    0.09
     سÙĪÙī
    0.09
    éĿĻéĿĻ
    0.09
    èµĦ产管çIJĨ
    0.09
    Activations Density 0.026%

    No Known Activations