© 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. 32142
    Prev
    Next
    INDEX
    Explanations

    cygwin, units, Over, traditional

    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
    驻马
    -0.08
    éĴĪ对æĢ§
    -0.08
     targeted
    -0.08
    综åIJĪå¾ģ
    -0.08
     Ãīr
    -0.08
    EMAT
    -0.08
    éĴĪ对
    -0.08
    æĥ³ä¸įåĪ°
    -0.07
    Ñİд
    -0.07
    riminator
    -0.07
    POSITIVE LOGITS
    andler
    0.08
    ("${
    0.07
     noc
    0.06
     Concord
    0.06
    grav
    0.06
     freely
    0.06
     Äij
    0.06
    ession
    0.06
     Stick
    0.06
     (!!
    0.06
    Activations Density 0.001%

    No Known Activations