© 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. 3486
    Prev
    Next
    INDEX
    Explanations

    .tab

    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
    alia
    -0.08
    idia
    -0.07
    ↵  ↵
    -0.07
    ardini
    -0.07
    æĺ±
    -0.07
    ë¹Ī
    -0.07
    anel
    -0.06
    ↵   ↵
    -0.06
    åĪ¹
    -0.06
    ulario
    -0.06
    POSITIVE LOGITS
    jš
    0.07
    æĮĩæŃ£
    0.07
    iez
    0.07
    æ°´äºķ
    0.07
     Goodman
    0.07
     Diz
    0.07
    -tab
    0.06
    çĤ¹åĩ»åı³ä¸Ĭè§Ĵ
    0.06
    _POL
    0.06
    tab
    0.06
    Activations Density 0.147%

    No Known Activations