© 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. 13758
    Prev
    Next
    INDEX
    Explanations

    find or determine what to find

    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
     ugyanis
    -0.09
    umbo
    -0.09
    ä½łæĺ¯ä¸Ģ个
    -0.07
    ÑĢÑĥк
    -0.07
    ấm
    -0.07
    обоÑĢоÑĤ
    -0.07
    ëħIJ
    -0.07
    å·¥ä¸ļåĴĮä¿¡æģ¯åĮĸ
    -0.07
    Äįas
    -0.07
    active
    -0.07
    POSITIVE LOGITS
    çĶ±æѤ
    0.08
     whether
    0.07
    以æŃ¤ä¸º
    0.07
    以æѤ
    0.07
    ervlet
    0.07
    é»į
    0.07
    ãģĿãĤĮãĤĴ
    0.07
    бÑĥеÑĤÑģÑı
    0.07
    åı¯æĥ³èĢĮçŁ¥
    0.06
     thereafter
    0.06
    Activations Density 0.209%

    No Known Activations