© 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. 37973
    Prev
    Next
    INDEX
    Explanations

    citations

    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
    ัà¸Ļ
    -0.08
    ä¸Ģäºĭ
    -0.08
    auga
    -0.08
    ington
    -0.07
    isson
    -0.07
    >true
    -0.07
    irty
    -0.07
    Ø°Ùī
    -0.07
    egar
    -0.07
    isso
    -0.07
    POSITIVE LOGITS
    åĪĨåĪ«
    0.07
    åĪĨåĪ«ä¸İ
    0.07
    è¿Ļ两天
    0.07
    ande
    0.07
    ign
    0.07
    å¨ħ
    0.06
    ãĤģãģ§
    0.06
    ahr
    0.06
    yles
    0.06
    åĪĨåĪ¥
    0.06
    Activations Density 0.086%

    No Known Activations