© 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. 34076
    Prev
    Next
    INDEX
    Explanations

    gravitational lensing

    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
    verband
    -0.08
     ãĤ¹ãĥĿãĥ³ãĤµãĥ¼ãĤµãĤ¤ãĥĪ
    -0.08
    issen
    -0.08
    æĶ¶åħ¥åĴĮ
    -0.08
     industr
    -0.08
    Ứ
    -0.08
    вл
    -0.08
    ferien
    -0.07
    æľ¬ç½ij
    -0.07
     krimin
    -0.07
    POSITIVE LOGITS
    _tests
    0.08
     recoil
    0.07
     doubling
    0.07
     corrections
    0.07
    ä¸īä½ĵ
    0.07
     predicts
    0.07
     gravitational
    0.07
    elastic
    0.06
    æķ°æį®å¤ĦçIJĨ
    0.06
    çݯ
    0.06
    Activations Density 0.001%

    No Known Activations