© 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. 14690
    Prev
    Next
    INDEX
    Explanations

    "thus, wherein, applications"

    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
    è¿ľ
    -0.08
     Looks
    -0.07
    ä¼¼ä¹İ
    -0.07
    Looks
    -0.07
    èī¾å°Ķ
    -0.07
    Lorem
    -0.07
    erokee
    -0.07
     zda
    -0.07
     supposedly
    -0.06
    .tc
    -0.06
    POSITIVE LOGITS
    maz
    0.08
    æīĢ以说
    0.07
    è¿ĶåĽŀé¦ĸ页
    0.07
    Again
    0.07
    åľ¨ä½łçļĦ
    0.07
    æķħèĢĮ
    0.07
     caution
    0.06
    Therefore
    0.06
    以西
    0.06
    ierno
    0.06
    Activations Density 0.001%

    No Known Activations