© 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. 30023
    Prev
    Next
    INDEX
    Explanations

    Totally .ViewGroup, gpu, test

    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
    æ±°
    -0.08
    èļ£
    -0.08
    êµīìŀ¥
    -0.08
     Calon
    -0.08
    weis
    -0.08
     tiên
    -0.07
    ìıŁ
    -0.07
    ëį°ìĿ´íĬ¸
    -0.07
    ìĹIJ
    -0.07
     ëĮĢë¡ľ
    -0.07
    POSITIVE LOGITS
    ality
    0.09
    hetto
    0.08
     nhau
    0.08
    -sama
    0.07
    ed
    0.07
    è¿Ļä¹Ł
    0.07
    wealth
    0.07
    çĦ¶å¤§
    0.07
    est
    0.07
    isseur
    0.07
    Activations Density 0.004%

    No Known Activations