© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 26877
    Prev
    Next
    INDEX
    Explanations

    copyright notice, constructive, Description of, sandbox, Duplicate, drink

    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
    esda
    -0.07
    arbeiter
    -0.07
    urf
    -0.07
    éĻĦè¿ijæľī
    -0.07
    ophone
    -0.07
    enders
    -0.07
    ä»Ģä¹Īåij¢
    -0.07
    奸
    -0.06
    à¸Ħรà¸Ńà¸ĩ
    -0.06
    å®ģåı¯
    -0.06
    POSITIVE LOGITS
    hausen
    0.08
    è¨Ģä¼ł
    0.07
    æĿĸ
    0.07
    桦
    0.07
    gua
    0.07
    _extract
    0.07
    æª
    0.07
    джа
    0.07
    æijĺ
    0.07
    اÙĨت
    0.07
    Activations Density 0.011%

    No Known Activations