© 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. 64561
    Prev
    Next
    INDEX
    Explanations

    Cheng names and places

    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
    HING
    -0.09
    faction
    -0.09
    schild
    -0.09
    Ø©
    -0.09
    edException
    -0.08
    WAYS
    -0.08
    cloak
    -0.08
    ÙģÙĤØ©
    -0.08
    ï¸ı
    -0.08
    IGIN
    -0.08
    POSITIVE LOGITS
    åIJīæĢĿ
    0.13
    äºĨä¸Ģç§į
    0.08
     tá»±u
    0.08
    uria
    0.07
    ularity
    0.07
    der
    0.07
    äºĨä¸ĢèĪ¬
    0.07
    richt
    0.07
    ning
    0.07
    atters
    0.07
    Activations Density 0.007%

    No Known Activations