© 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. 46057
    Prev
    Next
    INDEX
    Explanations

    time units and distance

    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
    moz
    -0.08
    oned
    -0.07
     же
    -0.07
    ç«ł
    -0.06
     bon
    -0.06
    è£ħä¸Ĭ
    -0.06
    /MIT
    -0.06
    puted
    -0.06
    èĩªéĢī
    -0.06
    ozilla
    -0.06
    POSITIVE LOGITS
    çĻ¾æĪĺ
    0.08
    atil
    0.07
     tát
    0.07
    voyer
    0.07
    yla
    0.07
    &action
    0.07
    laf
    0.07
    æĪij为
    0.07
    etre
    0.07
     hare
    0.07
    Activations Density 0.022%

    No Known Activations