© 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. 47068
    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
    ãĥ«ãĥ¼ãĥł
    -0.07
    ppen
    -0.07
    éĵĽ
    -0.07
     flexGrow
    -0.07
     Katzen
    -0.07
    çļĦ羣
    -0.07
    èĬ®
    -0.07
    书å±ĭ
    -0.07
     //~
    -0.07
    ogna
    -0.07
    POSITIVE LOGITS
    çıĬ
    0.08
    ocode
    0.08
    _BAR
    0.07
    _OM
    0.07
     Vict
    0.06
     gent
    0.06
    å®Ŀé¾Ļ
    0.06
     Dar
    0.06
    åĵº
    0.06
     ÐijаÑĢ
    0.06
    Activations Density 0.000%

    No Known Activations