© 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. 49240
    Prev
    Next
    INDEX
    Explanations

    half or fractional amounts

    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
    ãĥIJãĥª
    -0.09
    isso
    -0.08
    isman
    -0.08
    rän
    -0.08
    ç±
    -0.08
    åĨĽæ°ij
    -0.07
     Airways
    -0.07
    è¶Ĭ强
    -0.07
    ãĥģãĥ¥ãĥ¼
    -0.07
    ÙĪبÙĬ
    -0.07
    POSITIVE LOGITS
     halves
    0.10
    half
    0.10
    -half
    0.10
    ä¸ĢåįĬ
    0.10
     half
    0.10
    åĩıåįĬ
    0.09
     Half
    0.08
    å¹³åĪĨ
    0.08
    äºĨä¸ĢåįĬ
    0.07
     Halb
    0.07
    Activations Density 0.014%

    No Known Activations