© 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. 22572
    Prev
    Next
    INDEX
    Explanations

    rearrangement

    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
    æĹłå¿Į
    -0.07
    认罪
    -0.07
    æ¹¾
    -0.07
    å§Ĺ
    -0.06
     mainten
    -0.06
    ä½ķ
    -0.06
    ivin
    -0.06
     cycles
    -0.06
    åħ±åĴĮ
    -0.06
    裸
    -0.06
    POSITIVE LOGITS
    bras
    0.08
    lege
    0.08
    alts
    0.07
    omber
    0.07
    æīĶåĪ°
    0.07
    çļĦ鼨
    0.07
    anse
    0.07
    ueur
    0.07
     Chore
    0.07
    .Annotation
    0.07
    Activations Density 0.002%

    No Known Activations