© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 48263
    Prev
    Next
    INDEX
    Explanations

    flooring and tiles

    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
    æłijä¸ĬçļĦ
    -0.08
    ntag
    -0.07
    å®Ī
    -0.07
    Shirt
    -0.07
    fatt
    -0.07
    æłijä¸Ĭ
    -0.07
    æĭĨ解
    -0.07
    æ¡ħ
    -0.07
    tower
    -0.07
    esper
    -0.07
    POSITIVE LOGITS
     flooring
    0.12
    éĵºè®¾
    0.11
    èĢIJ磨
    0.11
    éĵº
    0.10
    åľ°çłĸ
    0.10
    éĺ²æ»ij
    0.10
     tiles
    0.10
    éĵºè£ħ
    0.10
     tile
    0.09
    .tile
    0.09
    Activations Density 0.070%

    No Known Activations