© 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. 46613
    Prev
    Next
    INDEX
    Explanations

    atrophy, denervation, disease

    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
    umin
    -0.07
    ç¡Ģ
    -0.07
    æķĻå¸Īè¦ģ
    -0.06
     dure
    -0.06
     ad
    -0.06
     j
    -0.05
    awning
    -0.05
    ä¸½å¨ľ
    -0.05
    ension
    -0.05
     ind
    -0.05
    POSITIVE LOGITS
    anio
    0.10
    çļĦè¿ĩç¨ĭä¸Ń
    0.08
    æĬ¬
    0.08
    ongi
    0.08
    ãģ¨è¨Ģãģ£ãģ¦ãĤĤ
    0.08
    使å¾Ĺ
    0.08
    è¶ĬæĹ©
    0.08
    DialogTitle
    0.08
    çļĦåIJĮæŶ
    0.08
    γεν
    0.08
    Activations Density 0.002%

    No Known Activations