© 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. 27171
    Prev
    Next
    INDEX
    Explanations

    width and height

    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
    ä¸ĵæłıæĶ¶å½ķ该åĨħ容
    -0.11
    çľ
    -0.07
     tril
    -0.07
    iales
    -0.07
    æĪĸåħ¶
    -0.07
    é¢Ħ
    -0.06
    éłIJ
    -0.06
    dale
    -0.06
    iali
    -0.06
     tr
    -0.06
    POSITIVE LOGITS
    agak
    0.08
    åĴĮåIJİ
    0.08
    æī¬éķ¿
    0.08
    ä¹Łå¥½
    0.07
    ä¹Łç½¢
    0.07
    çīĩåĴĮ
    0.07
    é¡¹çĽ®åĴĮ
    0.07
    åĴĮä¸ĭ
    0.07
    çIJĨäºĭ
    0.07
    åĩĿ
    0.07
    Activations Density 0.379%

    No Known Activations