© 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. 60374
    Prev
    Next
    INDEX
    Explanations

    solutions, condition, relevant, ordinary, already

    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
    apollo
    -0.09
    è°ĥåĬ¨
    -0.08
     Couleur
    -0.07
    ạp
    -0.07
     Prat
    -0.07
    éļ¶å±ŀ
    -0.07
     ngẫu
    -0.07
     random
    -0.07
     اÙĦØŃج
    -0.07
    äºĨ解ä¸Ģä¸ĭåIJ§
    -0.07
    POSITIVE LOGITS
     ghosts
    0.07
    oyer
    0.07
    ness
    0.07
    Ans
    0.07
    umann
    0.07
    esis
    0.07
     prih
    0.07
    åIJĪçIJĨæĢ§
    0.07
     Potter
    0.07
     acceptable
    0.06
    Activations Density 0.001%

    No Known Activations