© 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. 55485
    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
    orr
    -0.08
    xel
    -0.07
     Forever
    -0.07
    emann
    -0.07
    ideshow
    -0.07
    ndl
    -0.07
     Enf
    -0.06
    ORIA
    -0.06
     TestData
    -0.06
    è´Łè´£ç»Ħç»ĩ
    -0.06
    POSITIVE LOGITS
    æľīç§į
    0.08
    akis
    0.07
    hus
    0.07
    umba
    0.07
    hiba
    0.06
    mites
    0.06
    ç«ŀéĢŁ
    0.06
    laš
    0.06
    ä¼´ä½ł
    0.06
    Graphics
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.