© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 43241
    Prev
    Next
    INDEX
    Explanations

    adhesives, therapy, camera

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åijĹ
    -0.08
    äºİè¡Į
    -0.07
    åı¦è¡ĮéĢļçŁ¥
    -0.07
    æ¡Ī件éĢĤçĶ¨æ³ķå¾ĭ
    -0.07
    otta
    -0.07
    uvia
    -0.07
    KB
    -0.07
    ��
    -0.07
    ody
    -0.06
    ä»Ģä¹Īåı«
    -0.06
    POSITIVE LOGITS
    ä¹Ŀ天
    0.08
     напÑĢоÑĤив
    0.07
    以åıĬ
    0.07
    —which
    0.07
    imis
    0.07
     dewasa
    0.06
    ä¸įåı¯æĢĿè®®
    0.06
    ï¼Ī
    0.06
    天æŶ
    0.06
     ÐĴолоди
    0.06
    Activations Density 0.299%

    No Known Activations