© 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. 45996
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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
    uel
    -0.08
    emean
    -0.07
    Ñģл
    -0.07
    cak
    -0.07
    èįŁ
    -0.06
     incol
    -0.06
    æĺĵçĪĨ
    -0.06
    æĭ¶
    -0.06
    atables
    -0.06
    amenta
    -0.06
    POSITIVE LOGITS
    ords
    0.07
     inters
    0.07
    äºijå³°
    0.06
     Ïį
    0.06
    quir
    0.06
    èche
    0.06
    天ä¸ĭ
    0.06
    TERS
    0.06
    æĹģ
    0.06
    akra
    0.06
    Activations Density 0.004%

    No Known Activations