© 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. 7415
    Prev
    Next
    INDEX
    Explanations

    introductions and descriptions

    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
    _FINAL
    -0.07
    åIJĮæŶè¿ĺè¦ģ
    -0.07
    起订
    -0.07
    iring
    -0.07
    è¯Ńè¨ĢåĴĮ
    -0.07
    _ZERO
    -0.07
    erc
    -0.07
    _foreign
    -0.06
    æµİ
    -0.06
    å¦ĤæŀľåĨį
    -0.06
    POSITIVE LOGITS
    çĦ¶åIJİçĶ¨
    0.08
    çĦ¶åIJİ
    0.08
    Then
    0.08
    ::-
    0.07
    롤
    0.07
    çĦ¶åIJİæĬĬ
    0.07
     Then
    0.07
    çĦ¶åIJİå°±
    0.07
    baugh
    0.07
    æİ¥çĿĢ
    0.07
    Activations Density 0.024%

    No Known Activations