© 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. 42783
    Prev
    Next
    INDEX
    Explanations

    perspective projection geometry

    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
    adoo
    -0.07
    falls
    -0.07
    å®ļåĪ¶çļĦ
    -0.07
    comm
    -0.07
    å·¢æ¹ĸ
    -0.07
    )(((
    -0.07
    åĴĸåĸ±
    -0.07
    -lang
    -0.07
    rimon
    -0.07
    legate
    -0.07
    POSITIVE LOGITS
     centered
    0.09
    çļĦä¸Ńå¿ĥ
    0.08
    å°ĨçIJĥ
    0.07
     pupil
    0.07
    efs
    0.07
     centres
    0.07
    å°Ħ
    0.07
     اÙĦÙĤائÙħØ©
    0.07
     ÑĤоÑĩки
    0.07
    -cent
    0.07
    Activations Density 0.002%

    No Known Activations