© 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. 43509
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    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
    çģ«çĥ§
    -0.07
    eyond
    -0.07
    æĹĹé¼ĵ
    -0.07
    çıĬ
    -0.07
    amer
    -0.07
    Shapes
    -0.07
    åį¿
    -0.07
    è§Ħå¾ĭçļĦ
    -0.07
    ciÄĩ
    -0.07
    鲨
    -0.07
    POSITIVE LOGITS
    éĩijæ¡¥
    0.07
    ingleton
    0.07
    kä
    0.07
    nement
    0.07
    brid
    0.07
    aled
    0.07
    éĢĨåIJij
    0.07
    ноÑĢа
    0.06
    ç½®åľ°
    0.06
     unk
    0.06
    Activations Density 0.014%

    No Known Activations