© 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. 40375
    Prev
    Next
    INDEX
    Explanations

    math and numbers

    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
     rag
    -0.07
    éĢĢ票
    -0.07
     Feinstein
    -0.07
    yarat
    -0.07
    æĶ¶èµ·
    -0.07
    åIJIJ
    -0.07
    ç½Ħ
    -0.07
    MASK
    -0.07
    wich
    -0.07
    rag
    -0.07
    POSITIVE LOGITS
    å°ıç»ĦæĪIJåijĺ
    0.08
    quir
    0.07
    cube
    0.07
    Daemon
    0.07
    quirer
    0.07
    åĴĮçĽijçĿ£
    0.06
    share
    0.06
    Cube
    0.06
     Locker
    0.06
    breaker
    0.06
    Activations Density 0.008%

    No Known Activations