© 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. 39614
    Prev
    Next
    INDEX
    Explanations

    separately, individually, likewise

    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
    å§Ĭ妹
    -0.07
    urso
    -0.07
    gol
    -0.07
     fehl
    -0.06
     supplemented
    -0.06
    alli
    -0.06
     complement
    -0.06
    orni
    -0.06
     dup
    -0.06
    ulti
    -0.06
    POSITIVE LOGITS
    éĢIJ
    0.09
    åIJĮæŃ¥
    0.09
     separately
    0.09
    ä¹Łè·ŁçĿĢ
    0.08
    åīĶ
    0.08
     individually
    0.08
     оÑĤделÑĮно
    0.08
     ikut
    0.08
    éĢIJ项
    0.08
     likewise
    0.08
    Activations Density 0.055%

    No Known Activations