© 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. 7806
    Prev
    Next
    INDEX
    Explanations

    objects and subjects

    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
    anti
    -0.07
    awa
    -0.07
    gateway
    -0.07
    åºĩ
    -0.07
    æ¸łéģĵ
    -0.07
     gateway
    -0.07
    åĪ°ä½į
    -0.07
    åĴĮ使åij½
    -0.07
    Ĥ¬
    -0.07
    igation
    -0.07
    POSITIVE LOGITS
    çī©ä½ĵ
    0.12
    çī©ä½ĵçļĦ
    0.11
     objects
    0.11
    วัà¸ķà¸ĸุ
    0.09
     Objects
    0.09
    .objects
    0.09
    objects
    0.09
     обÑĬекÑĤÑĭ
    0.09
     обÑĬекÑĤов
    0.09
     object
    0.09
    Activations Density 0.096%

    No Known Activations