© 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. 1303
    Prev
    Next
    INDEX
    Explanations

    dimension

    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
    é»Ħç´ł
    -0.08
     #%
    -0.08
    éĢIJ
    -0.08
     expired
    -0.08
    ket
    -0.07
    ä¸Ģç³»åĪĹçļĦ
    -0.07
    æĪijçļĦå·¥ä½ľ
    -0.07
    κο
    -0.07
     Instant
    -0.07
     instinct
    -0.07
    POSITIVE LOGITS
     تعداد
    0.09
    еÑĤен
    0.08
    -dimensional
    0.08
    è¿ŀéĢļ
    0.08
     Ø´Ùħار
    0.07
    è³ĩ
    0.07
     count
    0.07
     dimensions
    0.07
    ptrdiff
    0.07
    çģ¾éļ¾
    0.07
    Activations Density 0.005%

    No Known Activations