© 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. 42564
    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
    ught
    -0.07
    ily
    -0.07
    ambre
    -0.07
    ovsky
    -0.07
    artes
    -0.07
    ее
    -0.07
    thr
    -0.07
    说åĪ°è¿ĻéĩĮ
    -0.07
    åĨħéļľ
    -0.07
    xim
    -0.07
    POSITIVE LOGITS
    rost
    0.08
    svp
    0.07
    éģ®
    0.07
     rabat
    0.07
    omar
    0.07
    rg
    0.07
     erk
    0.07
    непÑĢо
    0.07
    gelt
    0.06
    itant
    0.06
    Activations Density 0.000%

    No Known Activations