© 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. 14920
    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
    zeh
    -0.09
    á»Ļi
    -0.08
    mér
    -0.07
    æľīçIJĨ
    -0.07
     ode
    -0.07
    ãĤ·ãĥ£ãĥ¼
    -0.07
    atown
    -0.07
    è§Ħ模çļĦ
    -0.07
    teen
    -0.07
    æĮ¯åħ´
    -0.07
    POSITIVE LOGITS
    éĩijæŃ£
    0.07
    _PRIORITY
    0.07
    ä¼ĺåħĪ
    0.07
    æ³½æ°ij
    0.06
     Crane
    0.06
    æµģåĬ¨æĢ§
    0.06
    LM
    0.06
    /mobile
    0.06
    é¢ł
    0.06
    ä»ĬæľĿ
    0.06
    Activations Density 0.000%

    No Known Activations