© 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. 63424
    Prev
    Next
    INDEX
    Explanations

    physics, fluid dynamics, and computational methods

    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
    OrCreate
    -0.07
    åħ´åįİ
    -0.07
    å¼Ĥ彩
    -0.07
    berger
    -0.07
    ä¸įè¯Ń
    -0.07
    ô
    -0.07
    Stick
    -0.07
    _ident
    -0.07
    ikel
    -0.07
    ä½Ĩä¹Ł
    -0.06
    POSITIVE LOGITS
     effects
    0.09
    effects
    0.09
     consideration
    0.08
     Effects
    0.08
     corrections
    0.08
     ÑįÑĦÑĦекÑĤÑĭ
    0.08
    æѦéŃĤ
    0.07
    ogeneity
    0.07
    finite
    0.07
    æķĪåºĶ
    0.07
    Activations Density 0.020%

    No Known Activations