© 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. 14297
    Prev
    Next
    INDEX
    Explanations

    copyright notices and licenses

    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
    ÏĨÏħ
    -0.08
    ystal
    -0.08
    éħª
    -0.08
    {return
    -0.08
    è¦ģæī¾
    -0.08
     xÃŃch
    -0.08
    ELLO
    -0.08
    threat
    -0.08
    .future
    -0.08
    imea
    -0.08
    POSITIVE LOGITS
    äºĨä¸ĢåĪĩ
    0.06
    æĺ¯ä¸ĢåĪĩ
    0.06
    Contin
    0.06
    akens
    0.06
     pep
    0.06
    hofer
    0.06
    çļĦä¸ĢåĪĩ
    0.05
    Rendering
    0.05
     s
    0.05
    Ł
    0.05
    Activations Density 0.012%

    No Known Activations