© 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. 49783
    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
     mys
    -0.08
    æ·Ħ
    -0.08
    ifte
    -0.07
    ä¹ĭè¾Ī
    -0.07
    ä¹ĭä¸į
    -0.07
    ìĦ¼
    -0.07
    ONA
    -0.07
    enso
    -0.07
    owl
    -0.07
    erview
    -0.07
    POSITIVE LOGITS
    fty
    0.07
    à¸Ńà¸Ķ
    0.07
    åħ´
    0.07
    大åĪ©
    0.07
    ration
    0.06
    Pane
    0.06
    upati
    0.06
    æĪijåIJĹ
    0.06
    交çĶ±
    0.06
    odu
    0.06
    Activations Density 0.000%

    No Known Activations