© 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. 38187
    Prev
    Next
    INDEX
    Explanations

    units of measure following symbols

    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
    letal
    -0.08
    efeld
    -0.08
    enzo
    -0.07
    ('__
    -0.07
    enzen
    -0.07
    ebol
    -0.07
    alista
    -0.07
    nat
    -0.07
    eller
    -0.07
    æ¯ıä¸Ģ个åѦçĶŁ
    -0.07
    POSITIVE LOGITS
    å¤Ħ
    0.07
    iable
    0.06
     unre
    0.06
    iation
    0.06
    °
    0.06
    è£ĺ
    0.06
    isht
    0.06
    ëį°
    0.06
    工夫
    0.06
    Ñĥл
    0.06
    Activations Density 0.012%

    No Known Activations