© 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. 37933
    Prev
    Next
    INDEX
    Explanations

    even though

    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
    s
    -0.07
    Ģ
    -0.07
    sel
    -0.07
     denn
    -0.07
    å®ŀåľ¨å¤ª
    -0.06
    ÑĢÑĮ
    -0.06
    ighton
    -0.06
    ÑģÑı
    -0.06
    æģ©æĸ½
    -0.06
    ses
    -0.06
    POSITIVE LOGITS
     though
    0.11
    eens
    0.11
    ness
    0.10
    à¸ģระà¸Ĺัà¹Īà¸ĩ
    0.10
    ett
    0.09
     když
    0.09
    ews
    0.09
    beit
    0.08
    -handed
    0.08
    rette
    0.08
    Activations Density 0.042%

    No Known Activations