© 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. 63563
    Prev
    Next
    INDEX
    Explanations

    you followed by want or like

    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
    åĿĩåĮĢ
    -0.10
    éĢı
    -0.09
     cá»Ń
    -0.09
    ós
    -0.09
    OUTH
    -0.09
    ç»Ī身
    -0.09
    rying
    -0.09
     Coun
    -0.08
    æ¼±
    -0.08
    æĻħ
    -0.08
    POSITIVE LOGITS
    åįłæľī
    0.11
    æĤĦ
    0.09
    éĹªéĹª
    0.09
    åį°è±¡æ·±åĪ»
    0.09
    éĢĤçĶ¨
    0.08
    便åı¯
    0.08
    为代表
    0.08
    æĥ¯
    0.08
    ä¸ĩ个
    0.08
    æīįå¹²
    0.08
    Activations Density 0.027%

    No Known Activations