© 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. 62444
    Prev
    Next
    INDEX
    Explanations

    iOS commands

    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
    oret
    -0.07
     %#
    -0.07
    nnen
    -0.07
    -org
    -0.07
     Paren
    -0.07
     ort
    -0.07
    .tt
    -0.07
    ingo
    -0.07
     ot
    -0.07
    azi
    -0.06
    POSITIVE LOGITS
    cke
    0.07
    IOS
    0.07
    য়া
    0.07
    ä¸İä¸ĸçķĮ
    0.07
    åIJĦ个é¢ĨåŁŁ
    0.06
    acap
    0.06
    ä½ķåľ°
    0.06
     Schnee
    0.06
    Ñģие
    0.06
    cm
    0.06
    Activations Density 0.017%

    No Known Activations