© 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. 39176
    Prev
    Next
    INDEX
    Explanations

    diff context marker

    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
    áŀī
    -0.07
    å¿ĥæĤ¦
    -0.07
    ä¸Ń大
    -0.06
     ('
    -0.06
    ug
    -0.06
    .utility
    -0.06
    .hasOwnProperty
    -0.06
    åħ¬é¦Ĩ
    -0.06
     disb
    -0.06
    æĸĩçĮ®
    -0.06
    POSITIVE LOGITS
    olos
    0.08
    otis
    0.08
    ilos
    0.08
    olik
    0.07
    èĭ¦èĭ¦
    0.07
    æŀ¢
    0.07
    Ắ
    0.07
    arahan
    0.07
    åı°åīį
    0.07
    PLUS
    0.07
    Activations Density 0.128%

    No Known Activations