© 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. 19679
    Prev
    Next
    INDEX
    Explanations

    sequence of 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
    ÃŃn
    -0.08
    lac
    -0.07
    ä»ĭåħ¥
    -0.07
    alter
    -0.07
    oy
    -0.07
    lessness
    -0.06
    éįĬ
    -0.06
    opy
    -0.06
    èħ¹é»ij
    -0.06
    alon
    -0.06
    POSITIVE LOGITS
    ä½ľåĵģåĨħ容
    0.07
    akkan
    0.07
    aggio
    0.07
    ingers
    0.07
    ras
    0.07
     ras
    0.07
     roda
    0.07
    erah
    0.07
    uba
    0.07
    çĶŁåŃIJ女
    0.07
    Activations Density 0.004%

    No Known Activations