© 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. 22602
    Prev
    Next
    INDEX
    Explanations

    citations and URLs

    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
    麾
    -0.07
    çIJIJ
    -0.07
    å®ĥéĤ£
    -0.07
    ERG
    -0.07
    UF
    -0.07
    hone
    -0.06
    /documentation
    -0.06
    esh
    -0.06
    æľ¬ä¸ĵä¸ļ
    -0.06
    кала
    -0.06
    POSITIVE LOGITS
    ovid
    0.08
    avail
    0.07
    inius
    0.07
    AtIndex
    0.07
     str
    0.07
    uver
    0.07
    Ĭ
    0.07
    æĶ
    0.07
    åĴķ
    0.06
    skab
    0.06
    Activations Density 0.001%

    No Known Activations