© 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. 29391
    Prev
    Next
    INDEX
    Explanations

    probability sequences and formulas

    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
     Mund
    -0.09
    -parse
    -0.09
    constructed
    -0.08
    hares
    -0.08
     tille
    -0.08
    Specifier
    -0.08
    _AXIS
    -0.08
    踪影
    -0.07
    .sourceforge
    -0.07
    -sem
    -0.07
    POSITIVE LOGITS
    éĮ
    0.07
     vig
    0.07
    å®Ī
    0.07
    adelphia
    0.06
    ä¸Ĭä¸Ģ
    0.06
    ¤í
    0.06
     Raq
    0.06
    redo
    0.06
     nig
    0.06
     ÄįÃŃs
    0.06
    Activations Density 0.011%

    No Known Activations