© 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. 26183
    Prev
    Next
    INDEX
    Explanations

    in setting or account

    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
    æĹłè®ºä½ł
    -0.07
    ä¸įå¾Ĺ以任ä½ķ
    -0.07
    åĬĽå£«
    -0.07
    å¾Ĺèµ·
    -0.07
    å±ħçĦ¶æĺ¯
    -0.07
     Ponti
    -0.06
    ä¸įå¾Ĺ使çĶ¨
    -0.06
     Bris
    -0.06
     McGregor
    -0.06
    owel
    -0.06
    POSITIVE LOGITS
    ãģ©ãģĨãģĭ
    0.08
    ä½ľåĪĻ
    0.08
    å¤ĩçĶ¨
    0.07
    ÃīM
    0.07
    åį´å¾Ī
    0.07
    ë
    0.07
    类似éĹ®é¢ĺ
    0.07
    ziem
    0.07
    iev
    0.07
    ä¹Łæĺ¯ä¸Ģæł·
    0.07
    Activations Density 0.049%

    No Known Activations