© 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. 9351
    Prev
    Next
    INDEX
    Explanations

    numbers in code context

    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
    iph
    -0.07
    tvr
    -0.07
    eking
    -0.07
    åİĦ
    -0.07
     ins
    -0.07
    Å«t
    -0.06
    asan
    -0.06
    è®¤è®¤çľŁçľŁ
    -0.06
    san
    -0.06
    remen
    -0.06
    POSITIVE LOGITS
    ä¸įæĺ¯åIJĹ
    0.08
     etc
    0.08
    å¾Īå¤ļä¸ľè¥¿
    0.07
     ÙĪÙĩÙĥذا
    0.07
    åĨ²å¤©
    0.07
    ä¸Ń人
    0.07
     accordingly
    0.07
     Dagger
    0.07
    мам
    0.07
    .parseFloat
    0.07
    Activations Density 0.022%

    No Known Activations