© 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. 3747
    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
    arkin
    -0.08
    teken
    -0.08
    çļĦ建设
    -0.08
    construct
    -0.07
    iar
    -0.07
    esktop
    -0.07
    band
    -0.07
    ial
    -0.07
    åk
    -0.06
    建设
    -0.06
    POSITIVE LOGITS
    ombs
    0.08
    uhe
    0.07
    ÛĮب
    0.07
    çł¥
    0.07
    ihn
    0.07
    社åĨħ
    0.07
     Reactive
    0.07
    çĭ¬æľī
    0.07
    uzzy
    0.07
    æŁ¬
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.