© 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. 15241
    Prev
    Next
    INDEX
    Explanations

    alphanumeric characters, punctuation

    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
    æĢģ
    -0.07
    cker
    -0.07
    CKER
    -0.07
    MC
    -0.07
    anj
    -0.07
    端åĪ°
    -0.06
    é£İ头
    -0.06
    ucr
    -0.06
    Ãłn
    -0.06
    uno
    -0.06
    POSITIVE LOGITS
    ither
    0.07
    olley
    0.06
    erman
    0.06
    æīĢåľ¨
    0.06
     Dudley
    0.06
    ÛĮÙģ
    0.06
    ertian
    0.06
    ÙĪدÛĮ
    0.06
    ewa
    0.06
    λια
    0.06
    Activations Density 0.009%

    No Known Activations