© 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. 31107
    Prev
    Next
    INDEX
    Explanations

    parts of objects and their functions

    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
    rams
    -0.07
    hint
    -0.06
    hin
    -0.06
    çĿĢæĥ³
    -0.06
    ãĥĥãĥĶãĥ³ãĤ°
    -0.06
    1
    -0.06
    梯åŃIJ
    -0.05
    Âł
    -0.05
    士ãģ®
    -0.05
     conject
    -0.05
    POSITIVE LOGITS
    -like
    0.11
     whose
    0.10
    whose
    0.10
    类产åĵģ
    0.09
    éħį以
    0.09
    -style
    0.09
    ableObject
    0.09
     cuya
    0.09
    ä¸ĵçĶ¨çļĦ
    0.09
    ä¸Ģæł·çļĦ
    0.09
    Activations Density 0.096%

    No Known Activations