© 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. 13851
    Prev
    Next
    INDEX
    Explanations

    halfway between, plot scatter, Douglas discuss

    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
     ‘
    -0.07
    ‘
    -0.07
    elv
    -0.06
    ancel
    -0.06
    KEN
    -0.06
    æĸ°è¯¾ç¨ĭ
    -0.06
    azel
    -0.06
     Kron
    -0.06
    zin
    -0.06
     rumored
    -0.06
    POSITIVE LOGITS
    duk
    0.08
    ä¸½å¨ľ
    0.07
    åľ¨ä»ĬåIJİçļĦå·¥ä½ľä¸Ń
    0.07
    buzz
    0.07
    åľ¨é¦Ļ港
    0.07
    æĿ¥è¶Ĭ
    0.07
    çѱ
    0.07
    èĢĮå°±
    0.07
    WithValue
    0.07
    ượt
    0.07
    Activations Density 0.010%

    No Known Activations