© 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. 19775
    Prev
    Next
    INDEX
    Explanations

    strontium or cesium compounds

    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
    senz
    -0.08
    shed
    -0.08
    zicht
    -0.08
    icked
    -0.07
    ARD
    -0.07
    institu
    -0.07
    åľ¨çľī
    -0.07
    erti
    -0.07
    ered
    -0.07
    romise
    -0.07
    POSITIVE LOGITS
    PUBLIC
    0.07
    代表大ä¼ļ
    0.07
    /div
    0.07
     Luck
    0.06
     analog
    0.06
    ÅĤ
    0.06
     analogue
    0.06
    iski
    0.06
    fra
    0.06
    onia
    0.06
    Activations Density 0.008%

    No Known Activations