© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 64165
    Prev
    Next
    INDEX
    Explanations

    time after minutes

    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
    cmds
    -0.08
    elaar
    -0.08
    elps
    -0.08
    umat
    -0.08
    游æĪıç½ij
    -0.07
    tora
    -0.07
    åħ¨å·ŀ
    -0.07
    edor
    -0.07
    ä¸Ģæĸ°
    -0.07
    ë°¥
    -0.07
    POSITIVE LOGITS
    .hd
    0.08
    寡
    0.07
    ire
    0.07
    ist
    0.07
    arth
    0.07
    å¾®
    0.06
     dub
    0.06
    گار
    0.06
    æĬĢæľ¯åĬĽéĩı
    0.06
    oret
    0.06
    Activations Density 0.003%

    No Known Activations