© 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. 3972
    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
     csrf
    -0.08
     compet
    -0.07
    ↵                        ↵
    -0.06
     bid
    -0.06
    _tokenize
    -0.06
     subject
    -0.06
    æĬĺ
    -0.06
    DrawerToggle
    -0.06
     VO
    -0.06
    _restart
    -0.06
    POSITIVE LOGITS
    uhl
    0.08
    ttp
    0.08
    ailer
    0.08
    trap
    0.07
    izr
    0.07
    odal
    0.07
    æħĭ
    0.07
     بÙĨدÛĮ
    0.07
    aju
    0.07
    ä¸įå¹³
    0.07
    Activations Density 0.000%

    No Known Activations