© 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. 20538
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    æĿ¡
    -0.08
    owie
    -0.07
    åľ°äºļ
    -0.07
    efon
    -0.07
    æľīè¿ĩ
    -0.07
    outines
    -0.07
    isode
    -0.07
    å®ŀéĻħåĩºåıij
    -0.06
    illas
    -0.06
    pute
    -0.06
    POSITIVE LOGITS
    ingi
    0.07
    ollah
    0.07
    ÑģÑı
    0.07
    inol
    0.06
    ä½Ļåħī
    0.06
    èŀįåĮĸ
    0.06
     Visu
    0.06
    ани
    0.06
    дÑĥÑĪ
    0.06
    åħ¨
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.