© 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. 3127
    Prev
    Next
    INDEX
    Explanations

    evolution of, quality of, Terminus–Mahuva Express

    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
    ä¸Ģå¹´åĽĽåŃ£
    -0.07
    èļĢ
    -0.07
    mato
    -0.07
    mons
    -0.07
    elden
    -0.07
    essi
    -0.07
    жина
    -0.06
    ibi
    -0.06
    สà¸Ńà¸Ķ
    -0.06
    èĦ
    -0.06
    POSITIVE LOGITS
    ·¸
    0.08
    AGMA
    0.07
     pepe
    0.07
     (::
    0.07
    REFER
    0.07
    è¾¾åĨħ
    0.07
    为æĪij
    0.07
    nel
    0.06
    ilon
    0.06
    大è¯Ŀ
    0.06
    Activations Density 0.002%

    No Known Activations