© 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. 21796
    Prev
    Next
    INDEX
    Explanations

    units of measurement

    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
    bie
    -0.08
    bject
    -0.08
    CDATA
    -0.08
    ierge
    -0.08
    ×Ĺ×ķת
    -0.08
     ëŁ
    -0.07
    åĨį好
    -0.07
    è¾»
    -0.07
     ARISING
    -0.07
    enticate
    -0.07
    POSITIVE LOGITS
    å·¦åı³çļĦ
    0.08
    esh
    0.06
     Wonder
    0.06
    以ä¸ĭ为
    0.06
    é«ĺçļĦ
    0.06
    ÅĤon
    0.06
    æ·±çļĦ
    0.06
    以ä¸ĬçļĦ
    0.06
    以ä¸Ĭãģ®
    0.06
    V
    0.06
    Activations Density 0.376%

    No Known Activations