© 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. 31617
    Prev
    Next
    INDEX
    Explanations

    cells, receptors, regulatory

    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
    /buttons
    -0.08
    vand
    -0.07
    åıĬ设å¤ĩ
    -0.06
    isted
    -0.06
    οÏĢ
    -0.06
    unge
    -0.06
    estring
    -0.06
    æµģãĤĮ
    -0.06
    ourced
    -0.06
    .Components
    -0.06
    POSITIVE LOGITS
    åħ¼
    0.09
    åĬŁèĥ½çļĦ
    0.08
    èĥ½åĬĽçļĦ
    0.08
    åĬŁèĥ½
    0.08
    ingleton
    0.08
    çĭłçĭł
    0.08
    azy
    0.08
     tiá»ģm
    0.07
    eve
    0.07
    æ½ľåĬĽ
    0.07
    Activations Density 0.666%

    No Known Activations