© 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. 19486
    Prev
    Next
    INDEX
    Explanations

    Calculating mathematical expressions

    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
    antics
    -0.08
    edis
    -0.07
    rio
    -0.07
    Ģ
    -0.07
    ares
    -0.07
    oo
    -0.07
    naan
    -0.07
    ogi
    -0.07
    kee
    -0.06
    aggi
    -0.06
    POSITIVE LOGITS
    ¬
    0.09
    åĪ°çĽ®åīį
    0.08
    yleft
    0.08
    zeÅĽ
    0.07
    缸è¾ħ缸æĪIJ
    0.07
    åĬĽåĴĮ
    0.07
    éĴĪ对æĢ§çļĦ
    0.07
    _interfaces
    0.06
    richter
    0.06
    ¨
    0.06
    Activations Density 0.009%

    No Known Activations