© 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. 60828
    Prev
    Next
    INDEX
    Explanations

    parameter names or labels

    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
    ignon
    -0.07
    UCA
    -0.07
    为æĤ¨è§£çŃĶ
    -0.07
    pec
    -0.07
    orno
    -0.07
    eries
    -0.06
    å¾ĹåĩºçļĦ
    -0.06
    ergie
    -0.06
    cript
    -0.06
    EP
    -0.06
    POSITIVE LOGITS
    ä¸ĢåĪĨéĴ±
    0.07
    Anything
    0.07
    affle
    0.07
    _pointer
    0.07
    ım
    0.07
     overnight
    0.07
    çĪ±ä¸į
    0.07
    GROUND
    0.06
     AnyObject
    0.06
    æĺ¯ä¸Ģå¹´
    0.06
    Activations Density 0.001%

    No Known Activations