© 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. 25336
    Prev
    Next
    INDEX
    Explanations

    1 and $ symbols

    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
    ׼×Ŀ
    -0.08
     Heure
    -0.08
    å¿ĥæĥĬ
    -0.07
    æıIJ纲
    -0.07
    лÑij
    -0.07
    thal
    -0.07
    antara
    -0.07
    hec
    -0.07
    allas
    -0.07
    thon
    -0.07
    POSITIVE LOGITS
    avig
    0.08
    gnore
    0.07
    emas
    0.07
     tenuta
    0.07
    å®Ī
    0.07
    é¢IJ
    0.07
    laces
    0.07
    大ä¼ļ
    0.06
    ope
    0.06
    -val
    0.06
    Activations Density 0.005%

    No Known Activations