© 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. 27557
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions or equations

    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
    ä¸ĬçĻ¾
    -0.08
    à¤Ĥस
    -0.07
    <![
    -0.07
    éĢ¼äºº
    -0.07
    .Serializer
    -0.07
    ordan
    -0.07
    emor
    -0.07
     à¤Ĩधार
    -0.07
    ignano
    -0.07
    odi
    -0.07
    POSITIVE LOGITS
    ä¸įèĥ½æ»¡è¶³
    0.08
    ocop
    0.08
    ä¾ĽåºĶ产åĵģ
    0.08
    ç¬ĥ
    0.07
    à¹Īวà¸ĩ
    0.07
    ogue
    0.07
    ahal
    0.06
    rupt
    0.06
    价款
    0.06
    å¥ĩéģĩ
    0.06
    Activations Density 0.005%

    No Known Activations