© 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. 7357
    Prev
    Next
    INDEX
    Explanations

    vanishing

    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
    à¹Ģà¸Ħราะหà¹Į
    -0.07
    ç¯ī
    -0.07
    aversal
    -0.07
    à¹Ģห
    -0.07
    åĴĮåIJĦ
    -0.07
     Rij
    -0.07
    -counter
    -0.06
    ئاب
    -0.06
    ocha
    -0.06
    worthy
    -0.06
    POSITIVE LOGITS
    åĩ¡æĺ¯
    0.08
    éĥ¨åĪĨ
    0.08
    å±Ģéĥ¨
    0.08
    éĥ¨åĪĨçļĦ
    0.08
    åĩ¡
    0.07
    éĥ¨åĪĨæĺ¯
    0.07
     wherever
    0.07
    éĥ¨åĪĨãģ¯
    0.07
    æľīä¸Ģéĥ¨åĪĨ
    0.07
    ç¼ĺ
    0.07
    Activations Density 0.005%

    No Known Activations