© 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. 54388
    Prev
    Next
    INDEX
    Explanations

    regions or countries following 'in or 'of

    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
    é½
    -0.08
    rb
    -0.08
    flt
    -0.08
    æŁ¥çľĭ详æĥħ
    -0.08
    æ·¡
    -0.08
    éħª
    -0.08
    å§Ķä¼ļ
    -0.08
    à¸Ľà¸£à¸°
    -0.08
    æŀļ
    -0.08
    èĢķèĢĺ
    -0.08
    POSITIVE LOGITS
    åıĤè§Ĥ
    0.11
    æŃ£åĢ¼
    0.10
     Lesb
    0.10
    ä½İä¸ĭ
    0.09
    ç½Ł
    0.09
    è¯ļä¿¡
    0.09
    æĢĢ念
    0.08
    .Flag
    0.08
    éĻĭ
    0.08
    ||(
    0.08
    Activations Density 0.102%

    No Known Activations