© 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. 28138
    Prev
    Next
    INDEX
    Explanations

    numbers and variables in 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
    .nasa
    -0.08
    lee
    -0.07
    ghi
    -0.07
    achu
    -0.07
    combe
    -0.07
    åĮł
    -0.06
    è¿ĻäºĽæķ°æį®
    -0.06
     Islamabad
    -0.06
    ç¼ĺ
    -0.06
    ä¸įæķĮ
    -0.06
    POSITIVE LOGITS
    æĺ¯å¥½
    0.08
    iname
    0.08
    çı
    0.07
    _ENCODE
    0.07
    ziel
    0.07
    mun
    0.07
    cind
    0.07
    ÑĢин
    0.06
    ajuan
    0.06
    ÏĨι
    0.06
    Activations Density 0.001%

    No Known Activations