© 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. 27764
    Prev
    Next
    INDEX
    Explanations

    angles and rotation

    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
    ç³»æķ°
    -0.08
    atici
    -0.07
    æ·ĺæ±°
    -0.07
    æľ¬çº§
    -0.07
    UnderTest
    -0.07
     ãĤ¹ãĥĿãĥ³ãĤµãĥ¼ãĤµãĤ¤ãĥĪ
    -0.07
    chers
    -0.07
    pliers
    -0.07
    æ·¡åŃ£
    -0.07
    presa
    -0.07
    POSITIVE LOGITS
     radians
    0.08
    é£İåIJ¹
    0.07
     azimuth
    0.07
    geführt
    0.07
    riel
    0.07
    æŦ
    0.07
     giri
    0.07
    _signed
    0.07
    弧度
    0.07
     гÑĢадÑĥÑģ
    0.06
    Activations Density 0.007%

    No Known Activations