© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 33139
    Prev
    Next
    INDEX
    Explanations

    quoted punctuation or code

    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
    garan
    -0.07
    isse
    -0.06
    ×Ļ×Ķ
    -0.06
     Montgomery
    -0.06
    Overrides
    -0.06
    çīĪæĿĥå½ĴåİŁä½ľèĢħ
    -0.06
     Frid
    -0.06
    lin
    -0.06
    å°±å¾Ģ
    -0.06
    alc
    -0.06
    POSITIVE LOGITS
    çĤİ
    0.08
    à¸ŀร
    0.07
    è±¹
    0.07
    णà¥ĩ
    0.07
    ä¸ĭåľº
    0.07
    ãĥ»ãĥ»ãĥ»ãĥ»
    0.07
    ãĥ»ãĥ»ãĥ»ãĢĤ
    0.07
    #ad
    0.07
     umie
    0.07
    lag
    0.07
    Activations Density 0.441%

    No Known Activations