© 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. 3313
    Prev
    Next
    INDEX
    Explanations

    list item headers

    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
    asics
    -0.08
    éĢīæĭ©ä¸į
    -0.08
    Vien
    -0.07
    verb
    -0.07
    ehl
    -0.07
    house
    -0.07
    बà¤Ĥध
    -0.07
    Lorem
    -0.07
    лек
    -0.07
    çŀ»
    -0.07
    POSITIVE LOGITS
    âĢ§
    0.07
    /OR
    0.07
    æĢ»èĢĮè¨Ģä¹ĭ
    0.07
    /packages
    0.07
    endiendo
    0.07
    å¨Ĩ
    0.07
    illons
    0.07
     unveil
    0.06
     lÃłn
    0.06
     undoubtedly
    0.06
    Activations Density 0.005%

    No Known Activations