© 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. 19145
    Prev
    Next
    INDEX
    Explanations

    water purification and filtration

    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
    æģ¯
    -0.10
    åīª
    -0.09
    _FOREACH
    -0.09
    为èĩªå·±
    -0.09
    ä¹±
    -0.09
    áŀī
    -0.09
     scissors
    -0.09
    ä½İä¸ĭ
    -0.08
    غÙĨÙĬ
    -0.08
    lover
    -0.08
    POSITIVE LOGITS
    æ·¡åĮĸ
    0.10
    è¿ĩ滤
    0.10
    åľ¨çº¿
    0.10
    .reject
    0.09
    reject
    0.09
    Reject
    0.09
    fit
    0.09
    èĢģåŃIJ
    0.08
     flo
    0.08
    éĽĨä¸Ń
    0.08
    Activations Density 0.078%

    No Known Activations