© 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. 19767
    Prev
    Next
    INDEX
    Explanations

    mathematical functions and conditions

    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
    路桥
    -0.08
    峪
    -0.08
    åºķä»·
    -0.07
    uxt
    -0.07
    涯
    -0.07
    roc
    -0.07
    _DIAG
    -0.07
    erop
    -0.07
     फà¥Ī
    -0.07
    æ·¹
    -0.07
    POSITIVE LOGITS
    åħ³ç³»
    0.07
    ãĤĴæºĢãģŁ
    0.07
    oth
    0.07
    /epl
    0.07
    ç¥ŀç§ĺçļĦ
    0.07
    满足
    0.06
    å°Ħ
    0.06
     incons
    0.06
     relations
    0.06
     meets
    0.06
    Activations Density 0.010%

    No Known Activations