© 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. 9211
    Prev
    Next
    INDEX
    Explanations

    for good

    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
    tons
    -0.09
    å®ĺæĸ¹çīĪ
    -0.07
    uite
    -0.07
    রà§į
    -0.07
    undy
    -0.07
    tures
    -0.07
    oro
    -0.07
    çļĦç¾İ女
    -0.07
    ¬ģ
    -0.07
    ington
    -0.07
    POSITIVE LOGITS
    åĴĮ第
    0.08
    ald
    0.08
    illa
    0.08
    nable
    0.07
    ëį°
    0.07
    ×ķת
    0.07
    nda
    0.07
    ر
    0.07
    åĴĮ
    0.06
    วว
    0.06
    Activations Density 0.001%

    No Known Activations