© 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. 26440
    Prev
    Next
    INDEX
    Explanations

    floating point numbers and precision

    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
    aros
    -0.07
    loh
    -0.07
    SEND
    -0.07
    amia
    -0.07
     swath
    -0.07
    onne
    -0.07
    RICS
    -0.07
    acol
    -0.07
    Åľ
    -0.07
    §
    -0.07
    POSITIVE LOGITS
    specifier
    0.08
     kunj
    0.07
    -google
    0.07
    indel
    0.07
    jent
    0.07
    祸é¦ĸ
    0.06
    دÙĪÙĨ
    0.06
    etch
    0.06
    0.06
    没æľīåľ¨
    0.06
    Activations Density 0.004%

    No Known Activations