© 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. 44096
    Prev
    Next
    INDEX
    Explanations

    content for subscription

    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
    æ£ł
    -0.07
    ãĤĴç«ĭãģ¦
    -0.07
    (es
    -0.06
    acobian
    -0.06
    rowse
    -0.06
    imming
    -0.06
    _ctxt
    -0.06
    à¸Ħรัà¹īà¸ĩ
    -0.06
    ам
    -0.06
    atório
    -0.06
    POSITIVE LOGITS
    ä½Ĩä¸įéĻIJäºİ
    0.11
    enance
    0.11
    igna
    0.10
    editable
    0.09
    uke
    0.09
    ieux
    0.09
    æıIJè¦ģ
    0.09
    ainte
    0.09
    edly
    0.09
    nect
    0.09
    Activations Density 0.061%

    No Known Activations