© 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. 22529
    Prev
    Next
    INDEX
    Explanations

    key parameter names

    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
    ç½ij讯
    -0.07
    çļĦæĥħ
    -0.07
    ]("
    -0.06
    _IMPLEMENT
    -0.06
    /mit
    -0.06
     Geoffrey
    -0.06
    (if
    -0.06
    epass
    -0.06
    æĪĸåħ¶
    -0.06
    (and
    -0.06
    POSITIVE LOGITS
    agh
    0.07
    ajib
    0.07
    æŃ»
    0.07
     downs
    0.07
    çĭĤ
    0.07
    çŀij
    0.07
    ikh
    0.06
    åĩº
    0.06
    ston
    0.06
    é¦ĸ
    0.06
    Activations Density 0.063%

    No Known Activations