© 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. 2507
    Prev
    Next
    INDEX
    Explanations

    tech instruction and documentation

    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
    uml
    -0.06
    mts
    -0.06
    æŦ
    -0.06
    ä¸įåı¯åIJ¦è®¤
    -0.06
     above
    -0.06
    ILI
    -0.06
    .rawValue
    -0.06
    强è°ĥ
    -0.05
    æĪij们éĥ½çŁ¥éģĵ
    -0.05
    ä¹ĭäºĮ
    -0.05
    POSITIVE LOGITS
    åĪĺçķħ
    0.07
    รà¸Ļ
    0.07
    ulik
    0.07
    ymb
    0.07
    _side
    0.07
    .nz
    0.07
    OrFail
    0.07
     à¦ıমন
    0.07
     Moreira
    0.07
    éħ¸çĶľèĭ¦è¾£
    0.07
    Activations Density 0.017%

    No Known Activations