© 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. 21452
    Prev
    Next
    INDEX
    Explanations

    show that

    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
     Pinh
    -0.07
    orien
    -0.07
    cht
    -0.07
    LAB
    -0.06
     nomin
    -0.06
    asuk
    -0.06
    labs
    -0.06
    ckt
    -0.06
    are
    -0.06
    åı¯è¨Ģ
    -0.06
    POSITIVE LOGITS
    éĢļè¿ĩåĪĨæŀIJ
    0.09
     suficientes
    0.08
    ä¸į足以
    0.08
     sufficient
    0.08
    calcul
    0.07
     calcul
    0.07
     کاÙģÛĮ
    0.07
    足以
    0.07
    èĢĮå½Ĵ
    0.07
     suficiente
    0.07
    Activations Density 0.014%

    No Known Activations