© 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. 9626
    Prev
    Next
    INDEX
    Explanations

    if followed by question

    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
    emic
    -0.07
    elin
    -0.06
    omial
    -0.06
    olino
    -0.06
    ams
    -0.06
    edu
    -0.06
    bang
    -0.06
    åĮĸ为
    -0.06
    lay
    -0.06
    ToShow
    -0.06
    POSITIVE LOGITS
    åIJİèĢħ
    0.10
     latter
    0.09
     ello
    0.08
     Ø°ÙĦÙĥ
    0.08
    å°Ķé¡¿
    0.08
    éĢļåĪĻ
    0.08
    maal
    0.08
    ׼ף
    0.08
    ìĸ´ìĦľ
    0.08
     thereof
    0.07
    Activations Density 0.099%

    No Known Activations