© 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. 1390
    Prev
    Next
    INDEX
    Explanations

    double types object

    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
    ัà¸ļสà¸Ļ
    -0.07
     active
    -0.06
     recognize
    -0.06
    ulls
    -0.06
     recogn
    -0.06
    ames
    -0.06
    殿
    -0.06
    èĭŀ
    -0.06
    CEPT
    -0.06
     coloured
    -0.06
    POSITIVE LOGITS
    å¤įæĿĤçļĦ
    0.09
    Ñħай
    0.08
    å¤įæĿĤ
    0.08
    à¹ģà¸ģ
    0.08
    Injected
    0.08
    òng
    0.08
    .perform
    0.08
    æĸ¯é¡¿
    0.08
    itata
    0.08
    ierz
    0.07
    Activations Density 0.001%

    No Known Activations