© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 53091
    Prev
    Next
    INDEX
    Explanations

    remembering facts or past events

    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
    åİĨåı²ä¸Ĭ
    -0.11
    åı¦ä¸ĢåįĬ
    -0.10
    好çľĭ
    -0.09
     history
    -0.09
    åľ¨è¿ĩåİ»
    -0.09
     ìĹŃìĤ¬
    -0.09
    ä¸Ģèµ·æĿ¥
    -0.09
    åĪļåĪļ
    -0.09
    çĽ¸ä¼ł
    -0.09
    åĽĽé¡¹
    -0.08
    POSITIVE LOGITS
    èĩ³ä»Ĭ
    0.12
    ç»ĨèĬĤ
    0.11
    ä¾ĿçĦ¶
    0.10
    åIJĨ
    0.10
    åĪ°çİ°åľ¨
    0.10
    ä¾Ŀæŧ
    0.09
     ÑģоÑħÑĢани
    0.09
    åĢ¬
    0.09
    esseract
    0.09
    æµģæ°´
    0.09
    Activations Density 0.043%

    No Known Activations