© 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. 9741
    Prev
    Next
    INDEX
    Explanations

    IRT, structure, counter, couples, transport

    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
    tparam
    -0.08
    кÑģа
    -0.07
    esen
    -0.07
    hz
    -0.07
    izon
    -0.07
     Abstand
    -0.07
     Opinion
    -0.07
    Logger
    -0.07
    funcs
    -0.07
    åįģä¹Ŀ
    -0.07
    POSITIVE LOGITS
    åĮ¡
    0.09
     despe
    0.09
     knowing
    0.08
    å·²çŁ¥
    0.08
    å®ĪæģĴ
    0.08
     rearr
    0.08
    Knowing
    0.07
    ä¿Ŀå®Ī
    0.07
    åİ®
    0.07
    åĮ¹
    0.07
    Activations Density 0.004%

    No Known Activations