© 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. 45849
    Prev
    Next
    INDEX
    Explanations

    unnecessary expenses, ingredients, infection, problems

    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
    æľīæīĢæĢĿ
    -0.08
    maal
    -0.08
    ÑĢÑĮ
    -0.07
    ä¸įæ¸Ŀ
    -0.07
    éĢIJæ¸IJ
    -0.07
    æĽ´å¥½çļĦèĩªå·±
    -0.07
     partially
    -0.07
    اÛĮÛĮ
    -0.07
    OrFail
    -0.06
    ostr
    -0.06
    POSITIVE LOGITS
     unnecessary
    0.10
    ä¸įå¿ħè¦ģçļĦ
    0.10
    ä¸įå¿ħè¦ģ
    0.09
    没æľīå¿ħè¦ģ
    0.08
     inutile
    0.08
    å¤ļçļĦ
    0.08
    æĹłåħ³
    0.08
    ç¼Ģ
    0.08
    aneous
    0.07
    unn
    0.07
    Activations Density 0.005%

    No Known Activations