© 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. 13357
    Prev
    Next
    INDEX
    Explanations

    indoor environments

    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
     profits
    -0.07
    å±ķ示çļĦ
    -0.07
    çĽĹå¢ĵ
    -0.07
    端
    -0.07
    åĨĴ
    -0.06
    书çŃ¾
    -0.06
    åĪ»èĭ¦
    -0.06
    squeeze
    -0.06
     genome
    -0.06
    æĽ¬
    -0.06
    POSITIVE LOGITS
     indoors
    0.10
    rever
    0.09
    å¢ĻéĿ¢
    0.09
    声åѦ
    0.09
     indoor
    0.09
     acoustic
    0.08
    ä¸īéĿ¢
    0.08
    æģº
    0.08
     walls
    0.08
     clutter
    0.08
    Activations Density 0.024%

    No Known Activations