© 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. 39141
    Prev
    Next
    INDEX
    Explanations

    years, dates, or numbers

    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
    Ñģно
    -0.07
    第äºĶç«ł
    -0.07
    è·µ
    -0.06
    åħ·
    -0.06
    øv
    -0.06
    REAK
    -0.06
    家ä¹IJ
    -0.06
     Cia
    -0.06
    缨
    -0.06
    ä»ĭç»į
    -0.06
    POSITIVE LOGITS
     Indah
    0.07
    etz
    0.07
    gger
    0.07
     Tạp
    0.07
    çĻ¾åIJį
    0.07
    èIJ©
    0.07
    umpul
    0.07
     remer
    0.07
    å¦Ī
    0.07
    åIJĮæľŁ
    0.06
    Activations Density 0.061%

    No Known Activations