© 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. 28800
    Prev
    Next
    INDEX
    Explanations

    abbreviation, short, word, phrase

    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
    ÙĦÙĥ
    -0.07
    è¿½æŁ¥
    -0.06
    çIJ¦
    -0.06
     Wand
    -0.06
    社ä¼ļæķĪçĽĬ
    -0.06
    flags
    -0.06
    æij¸åºķ
    -0.06
    _FLAG
    -0.06
    éĢIJ
    -0.06
    Flag
    -0.06
    POSITIVE LOGITS
     hy
    0.08
    å¤įæĿĤ
    0.07
    VEC
    0.07
    æŀĦ
    0.07
    LowerCase
    0.07
    amel
    0.07
     gá»įn
    0.07
    -length
    0.07
    bidden
    0.07
    Smarty
    0.07
    Activations Density 0.006%

    No Known Activations