© 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. 3029
    Prev
    Next
    INDEX
    Explanations

    gravitational waves, forces, field, settling

    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
     didik
    -0.08
     obsta
    -0.08
    izu
    -0.08
    edom
    -0.08
    iates
    -0.08
    Ø©
    -0.07
    trand
    -0.07
    ÑģÑĤва
    -0.07
    hood
    -0.07
    erville
    -0.07
    POSITIVE LOGITS
    itational
    0.10
    ä½ľçĶ¨ä¸ĭ
    0.08
    itasi
    0.08
    isc
    0.07
    ichel
    0.07
    uit
    0.07
    hic
    0.07
    åľ°çļĦ
    0.06
    xce
    0.06
    ignano
    0.06
    Activations Density 0.007%

    No Known Activations