© 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. 21052
    Prev
    Next
    INDEX
    Explanations

    table formatting symbols

    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
    »
    -0.10
    Mahon
    -0.08
    ´
    -0.08
    azzi
    -0.08
     xì
    -0.07
     (~(
    -0.07
    iaux
    -0.07
    ÙĪÙĨÙĬس
    -0.07
    usti
    -0.07
    acas
    -0.07
    POSITIVE LOGITS
    0.07
    memberof
    0.07
    缸è¾ħ缸æĪIJ
    0.06
    å°ı康社ä¼ļ
    0.06
    åĭĩå¾Ģ缴åīį
    0.06
    sak
    0.06
    vore
    0.06
    ampaign
    0.06
    ero
    0.05
    AT
    0.05
    Activations Density 0.134%

    No Known Activations