© 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. 42629
    Prev
    Next
    INDEX
    Explanations

    annotation and annihilation

    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
    ë§ĪìŀIJ
    -0.08
    wards
    -0.08
    ÅĦska
    -0.08
    anova
    -0.08
    pto
    -0.08
    ücks
    -0.08
    нева
    -0.07
     latter
    -0.07
    hood
    -0.07
    íĴĪ
    -0.07
    POSITIVE LOGITS
    ormal
    0.10
    ذاÙĥ
    0.09
    ointed
    0.09
    ihilation
    0.09
    à¹Ģวียà¸Ļ
    0.08
    ثاÙĦ
    0.08
    thinkable
    0.08
    äºĨäºĭ
    0.08
    ihal
    0.08
    ersed
    0.08
    Activations Density 0.111%

    No Known Activations