© 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. 4529
    Prev
    Next
    INDEX
    Explanations

    normal, routine, ideas

    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
    inta
    -0.08
    çĸĻçĺ©
    -0.07
    åĩĭ
    -0.07
    ackson
    -0.07
    .setError
    -0.07
    ivic
    -0.07
    shire
    -0.07
    abar
    -0.07
    çĦ¦èĻij
    -0.07
    olv
    -0.07
    POSITIVE LOGITS
    主åĬ¨
    0.10
    æŃ£å¸¸
    0.09
    æŃ£å¸¸çļĦ
    0.09
    çİĭä¼Ł
    0.08
     routine
    0.08
    å¹³æŶçļĦ
    0.08
    æŃ£å¸¸è¿IJè¡Į
    0.08
    utre
    0.08
    çļĦæŃ£å¸¸
    0.08
    æŃ£éĿ¢
    0.07
    Activations Density 0.487%

    No Known Activations