© 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. 62173
    Prev
    Next
    INDEX
    Explanations

    invention relates in general

    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
    èĥĮçĿĢ
    -0.11
    ä¸įå®ī
    -0.09
    /from
    -0.09
    າ
    -0.08
    åºľ
    -0.08
    é¢ĩ
    -0.08
    åѦä¼ļäºĨ
    -0.08
    éĶħ
    -0.08
    èī®
    -0.08
    èĤĩ
    -0.08
    POSITIVE LOGITS
     kepada
    0.14
    ä¸İä¸ŃåĽ½
    0.13
    ä¸İåħ¶ä»ĸ
    0.12
    åĪ°
    0.11
     Ø¥ÙĦÙĬÙĩ
    0.10
    ToFront
    0.10
    ä¸İä¼Ĺ
    0.10
     Ø¥ÙĦÙī
    0.10
     Ø¥ÙĦÙĬÙĩا
    0.10
    â¾
    0.10
    Activations Density 0.280%

    No Known Activations