© 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. 14432
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with powers

    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
    ÅĤon
    -0.08
    رائ
    -0.08
    inari
    -0.08
    grama
    -0.08
    adini
    -0.08
    ings
    -0.07
    arau
    -0.07
    ä¸Ģéĥİ
    -0.07
    ÄĻc
    -0.07
    hof
    -0.07
    POSITIVE LOGITS
    åĬłæĭ¿å¤§
    0.08
    èıı
    0.07
    olia
    0.06
    缸è¾ħ缸æĪIJ
    0.06
    æĸ°åĬłåĿ¡
    0.06
    çĥĽ
    0.06
    isha
    0.06
    clin
    0.05
    èįł
    0.05
    ধান
    0.05
    Activations Density 0.005%

    No Known Activations