© 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. 41540
    Prev
    Next
    INDEX
    Explanations

    programming imports and semicolons

    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
    ä¾Ľå¤§å®¶åıĤèĢĥ
    -0.08
    åıĺæĽ´åīį
    -0.07
    ablish
    -0.07
    窥éķľ
    -0.07
    çŀ©
    -0.07
    æĿ¥ä¹ĭ
    -0.07
    ä¸įè´Ł
    -0.07
    oste
    -0.07
    åĽĽæĸ¹
    -0.07
    áz
    -0.07
    POSITIVE LOGITS
    ManagerInterface
    0.09
    jana
    0.08
    itik
    0.06
    å¦Ĥä½ķéĢļè¿ĩ
    0.06
    é³Ħ
    0.06
     Funk
    0.06
    oll
    0.05
     Else
    0.05
    æĮĩæŃ£
    0.05
    梨èĬ±
    0.05
    Activations Density 0.226%

    No Known Activations