© 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. 24804
    Prev
    Next
    INDEX
    Explanations

    ions, molecules, and elements

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    tract
    -0.08
    ä¸ĢæŦåıijçİ°
    -0.07
    ÑĻе
    -0.07
    累累
    -0.07
    åĵĪå°Ķ
    -0.07
    _PROPERTY
    -0.07
     charisma
    -0.07
    åŃ©
    -0.07
    æīĢæĢĿ
    -0.07
    奥åĪ©
    -0.07
    POSITIVE LOGITS
    åıĤä¸İ
    0.10
    åıĤä¸İçļĦ
    0.10
    åıĤä¸İåĪ°
    0.10
     adicional
    0.09
    åıĤä¸İäºĨ
    0.09
     involvement
    0.08
    è¿ĽæĿ¥
    0.08
    åħħ足
    0.08
    åħ±åIJĮåıĤä¸İ
    0.08
    edia
    0.08
    Activations Density 0.023%

    No Known Activations