© 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. 39069
    Prev
    Next
    INDEX
    Explanations

    nm, m, yr, l, px

    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
    urn
    -0.07
    管çIJĨåĴĮ
    -0.07
    back
    -0.06
    åį¡çļĦ
    -0.06
    ×Ŀ
    -0.06
    åľĪçļĦ
    -0.06
    ı
    -0.06
    å·®çļĦ
    -0.06
    iban
    -0.06
    ä¸ĸçļĦ
    -0.06
    POSITIVE LOGITS
    ç©´
    0.08
    å²Ń
    0.07
    Chooser
    0.07
    Contained
    0.07
    å¤Ħ以
    0.07
    äºĨä¸ĢåIJį
    0.07
    Loads
    0.07
    pera
    0.07
     Took
    0.07
    æĸ¹æīį
    0.07
    Activations Density 0.159%

    No Known Activations