© 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. 26251
    Prev
    Next
    INDEX
    Explanations

    and coherence, and pixel, and quantum, and service

    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
    æĢĿè·¯åĴĮ
    -0.07
    omar
    -0.07
    ä¸įä»ħåľ¨
    -0.07
    WithError
    -0.07
    .eng
    -0.07
     Objective
    -0.07
    ModelError
    -0.07
    uslim
    -0.07
    ophon
    -0.07
    Untitled
    -0.07
    POSITIVE LOGITS
    /or
    0.10
    æŶéĹ´æĿ¥
    0.09
    éĢĤå½ĵçļĦ
    0.08
    éĢĤå½ĵ
    0.07
    /o
    0.07
    полне
    0.07
    åIJį人
    0.07
     Ú©ÙħÛĮ
    0.07
    andom
    0.07
    lop
    0.07
    Activations Density 0.074%

    No Known Activations