© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 22689
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with symbols

    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
    ç½Ĺå¾·
    -0.07
    XC
    -0.07
     Gam
    -0.06
    èĢĮ以
    -0.06
    oma
    -0.06
    sw
    -0.06
    轻工
    -0.06
    Ñħов
    -0.06
     ROD
    -0.06
    è§Ĩ
    -0.06
    POSITIVE LOGITS
    alah
    0.08
    anding
    0.08
    ilers
    0.08
    á»ijn
    0.07
    adier
    0.07
    ERING
    0.07
    arra
    0.07
    bacher
    0.07
    çīĽç¾Ĭ
    0.07
    ặng
    0.07
    Activations Density 0.023%

    No Known Activations