© 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. 57688
    Prev
    Next
    INDEX
    Explanations

    LaTeX math, code delimiters, and database column names

    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
    åıĬæŶåıijçİ°
    -0.08
    lendir
    -0.07
    oten
    -0.07
    缴æİ¥å°Ĩ
    -0.07
    以轻
    -0.07
    alsa
    -0.06
    illet
    -0.06
     strconv
    -0.06
    utra
    -0.06
    ãĥĨãĥ³
    -0.06
    POSITIVE LOGITS
    ÑĢеа
    0.08
    çĭ¬ç§Ģ
    0.07
    çī©
    0.07
    zni
    0.07
    ourke
    0.06
    assen
    0.06
    ENTO
    0.06
    社åĮºçļĦ
    0.06
    und
    0.06
     monoc
    0.06
    Activations Density 0.004%

    No Known Activations