© 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. 4489
    Prev
    Next
    INDEX
    Explanations

    Firm, Church, snakes, volumes, West, County, diving, cross

    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
    lieb
    -0.07
    -scalable
    -0.07
    rew
    -0.06
    èĴĻ
    -0.06
    hev
    -0.06
    è¡Ģ
    -0.06
    amy
    -0.06
    åĽº
    -0.06
    sek
    -0.06
    EEK
    -0.06
    POSITIVE LOGITS
    çŃīåħ¶ä»ĸ
    0.14
     later
    0.12
    æīį对
    0.10
    ä¹ŁåIJĮæł·
    0.10
    åIJİæĿ¥
    0.09
    æīįæĺ¯çľŁæŃ£çļĦ
    0.09
     später
    0.08
     ëĤĺì¤ijìĹIJ
    0.08
     Later
    0.08
    æīįæĺ¯
    0.08
    Activations Density 0.288%

    No Known Activations