© 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. 11101
    Prev
    Next
    INDEX
    Explanations

    magnitudes, circumference, velocity, angle, radius, speed

    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
    èIJ½èĬ±
    -0.08
    èches
    -0.08
    меÑģ
    -0.08
    &T
    -0.08
    æĶ¶èĹıæľ¬ç«Ļ
    -0.07
    èche
    -0.07
     aperto
    -0.07
     Erect
    -0.07
    &D
    -0.07
    äger
    -0.07
    POSITIVE LOGITS
    åľ¨æŁIJ
    0.07
    åĪĨå¸ĥå¦Ĥä¸ĭ
    0.07
     suddenly
    0.06
    åijĬè¯īä½ł
    0.06
    æ¯Ķ为
    0.06
     Suddenly
    0.06
    ç¹ģä½ĵ
    0.05
    çIJ¥
    0.05
    ãĢģ
    0.05
     continuously
    0.05
    Activations Density 0.057%

    No Known Activations