© 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. 7777
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and 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
    oot
    -0.08
    stadt
    -0.07
    ernals
    -0.07
    ensk
    -0.07
    icum
    -0.07
    enth
    -0.07
    upt
    -0.07
    thora
    -0.07
    elay
    -0.07
    pay
    -0.07
    POSITIVE LOGITS
    lander
    0.07
     adem
    0.07
    ença
    0.07
    iho
    0.07
     Lynch
    0.07
    angled
    0.07
    orre
    0.07
    丽èİİ
    0.07
    éĤ£ä¹ĪçļĦ
    0.06
    ÙĪÙĪ
    0.06
    Activations Density 0.013%

    No Known Activations