© 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. 13488
    Prev
    Next
    INDEX
    Explanations

    number of rows or count

    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
    heur
    -0.07
     entr
    -0.07
    ä¸Ńä¹ĭ
    -0.07
    èĭĽåĪ»
    -0.07
    漪
    -0.06
    è¿·ç³Ĭ
    -0.06
    ippo
    -0.06
    roku
    -0.06
    ½
    -0.06
    鼷
    -0.06
    POSITIVE LOGITS
     пÑĢон
    0.08
    IfExists
    0.08
    .xlim
    0.08
     insgesamt
    0.08
     Beyond
    0.08
     numbered
    0.08
    æī©å±ķåĪ°
    0.08
    iers
    0.07
    inea
    0.07
    æĢ»åħ±
    0.07
    Activations Density 0.050%

    No Known Activations