© 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. 8643
    Prev
    Next
    INDEX
    Explanations

    appellant or appellee

    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
    æŃ£è¦ı
    -0.08
    ippy
    -0.07
    osz
    -0.07
    oque
    -0.07
     ken
    -0.07
    ä½ĵç³»
    -0.07
    ä¸ĢåłĤ
    -0.07
    ouce
    -0.07
    ofday
    -0.06
    èĬĿ
    -0.06
    POSITIVE LOGITS
     portions
    0.13
    éĥ¨åĪĨçļĦ
    0.12
     portion
    0.11
    ä¸Ģ并
    0.11
     separately
    0.10
     separate
    0.10
     unrelated
    0.10
     Separate
    0.09
    éĥ¨åĪĨ
    0.09
    两éĥ¨åĪĨ
    0.09
    Activations Density 0.101%

    No Known Activations