© 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. 24917
    Prev
    Next
    INDEX
    Explanations

    volume fraction percentage

    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
    å½ĵä¹ĭ
    -0.07
     strtotime
    -0.07
    à¸ŀิ
    -0.07
    nica
    -0.07
    ä¸Ģä½ĵæľº
    -0.07
    rica
    -0.06
    zig
    -0.06
    åĽłäººèĢĮå¼Ĥ
    -0.06
    strtotime
    -0.06
    oncini
    -0.06
    POSITIVE LOGITS
     (%)
    0.09
    çĻ¾åĪĨä¹ĭ
    0.08
     percentages
    0.07
    ingan
    0.07
    ffre
    0.07
    ongan
    0.07
    cac
    0.07
     fractions
    0.07
    æݺ
    0.07
    å°Ķé¡¿
    0.07
    Activations Density 0.005%

    No Known Activations