© 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. 12909
    Prev
    Next
    INDEX
    Explanations

    basics

    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
    åīįè¿°
    -0.09
    .").
    -0.09
    éĢļè¿ĩè¿ĻäºĽ
    -0.09
    ä¸ĭä¸Ģç«ł
    -0.08
     **.**
    -0.08
    اÙģÙĦ
    -0.08
    ило
    -0.08
    ®,
    -0.08
    æ´»åĬ¨çŃī
    -0.08
    ilon
    -0.08
    POSITIVE LOGITS
     vs
    0.09
     nutshell
    0.07
     basics
    0.07
    é¦ĸåħĪéľĢè¦ģ
    0.07
    -
    0.07
    æ¦Ĥè¿°
    0.07
     Basics
    0.07
    åĨħ容ç®Ģä»ĭ
    0.07
    åŁºæľ¬æĥħåĨµ
    0.07
    âĢIJ
    0.07
    Activations Density 0.040%

    No Known Activations