© 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. 18575
    Prev
    Next
    INDEX
    Explanations

    lime, limestone, calcium, carbonate

    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
    ikov
    -0.08
     xếp
    -0.08
    umer
    -0.08
     Mitra
    -0.08
    reno
    -0.08
    imenta
    -0.08
    terr
    -0.08
    szak
    -0.08
    araan
    -0.07
    /stream
    -0.07
    POSITIVE LOGITS
    çŁ³çģ°
    0.10
     Ca
    0.08
     carbonate
    0.08
    è¡¥éĴĻ
    0.08
     gypsum
    0.08
    esan
    0.07
    Ca
    0.07
    çŁ³èĨı
    0.07
    o
    0.07
    çªij
    0.07
    Activations Density 0.005%

    No Known Activations