© 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. 37969
    Prev
    Next
    INDEX
    Explanations

    probability or sequence

    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
     ÐļÑĢаÑģи
    -0.08
    aty
    -0.08
    å®Ŀé¾Ļ
    -0.08
    ÑĢож
    -0.08
    adius
    -0.08
     СÑĤепа
    -0.07
    Ø´Ùħ
    -0.07
    ุà¸ĩ
    -0.07
    getManager
    -0.07
     ÐŁÐ¾Ð¿ÑĢо
    -0.07
    POSITIVE LOGITS
    è®´
    0.06
    ousse
    0.06
    ida
    0.06
    ÑģловиÑı
    0.05
    ç¥ĸ
    0.05
    uttle
    0.05
    è´¸
    0.05
    æ±°
    0.05
    oyo
    0.05
    Ŀ¼
    0.05
    Activations Density 2.979%

    No Known Activations