© 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. 29851
    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
    óÅĤ
    -0.08
    大æīĵ
    -0.07
    ÅŁtir
    -0.07
    igos
    -0.07
    osh
    -0.07
     helsing
    -0.06
    åĩ«
    -0.06
    èį¡
    -0.06
    ogg
    -0.06
     ÏĥÏĩε
    -0.06
    POSITIVE LOGITS
    åĭĩå¾Ģ缴åīį
    0.08
    anj
    0.07
    åĴļåĴļ
    0.07
    yje
    0.07
     Licensed
    0.07
     Guz
    0.07
     بشر
    0.06
    ujan
    0.06
    èĤ¥å¤§
    0.06
    å²ģæŶ
    0.06
    Activations Density 0.055%

    No Known Activations