© 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. 49830
    Prev
    Next
    INDEX
    Explanations

    educational contexts

    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
    )":
    -0.08
    ÎŃÏģγ
    -0.07
    -plus
    -0.07
    ):**
    -0.07
    )").
    -0.07
     оÑģÑĤалÑĮнÑĭе
    -0.07
     demás
    -0.07
    Å¡ten
    -0.07
    HWND
    -0.07
    èĻ¹æ¡¥
    -0.07
    POSITIVE LOGITS
    å°¤åħ¶åľ¨
    0.11
    å°¤åħ¶
    0.09
    å°¤åħ¶æĺ¯åľ¨
    0.09
    çī¹åĪ«æĺ¯åľ¨
    0.09
    æľ¬ç¯ĩ
    0.09
    å°¤åħ¶æĺ¯
    0.08
    ä¹Łè¶ĬæĿ¥è¶Ĭ
    0.08
    è¶ĬæĿ¥è¶Ĭ
    0.08
    çī¹åĪ«æĺ¯
    0.07
     especially
    0.07
    Activations Density 1.590%

    No Known Activations