© 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. 58630
    Prev
    Next
    INDEX
    Explanations

    will cause

    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
    еÑĨ
    -0.08
    ¹
    -0.08
    ë¦ĩ
    -0.07
    iewicz
    -0.07
    rim
    -0.07
    erweise
    -0.07
    æľīåĪ«
    -0.07
    ÑģоÑģ
    -0.07
    abb
    -0.07
    asm
    -0.07
    POSITIVE LOGITS
     Äijặn
    0.10
    /is
    0.09
    ียà¸ĩ
    0.09
    æľīæķĪæŀľ
    0.09
    çĶ¨åĪ°
    0.09
    ãģĺãĤģãģ¦
    0.08
    Ø©
    0.08
    æľīä¸Ģçķª
    0.08
    -be
    0.08
    aturally
    0.08
    Activations Density 0.002%

    No Known Activations