© 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. 15161
    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
    ä¹Łæľīå¾Īå¤ļ
    -0.07
     Cristal
    -0.07
    临
    -0.06
    åįĥåįĥ
    -0.06
     there
    -0.06
    arpa
    -0.06
    OMPI
    -0.06
    _ser
    -0.06
    并æİ¥åıĹ
    -0.06
    auge
    -0.06
    POSITIVE LOGITS
    usen
    0.08
    coni
    0.07
    øs
    0.07
    моÑĢа
    0.07
    constructed
    0.07
     revamped
    0.07
    leigh
    0.07
    æĥ³åĪ°äºĨ
    0.07
     tweaked
    0.07
    tright
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.