© 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. 65302
    Prev
    Next
    INDEX
    Explanations

    optical interference and metrology

    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
    æīĭèĦļ
    -0.07
    åħ³åı£
    -0.07
     detox
    -0.07
     Lump
    -0.07
    è½
    -0.07
     anthrop
    -0.07
     Bolt
    -0.06
    ç¥ŀç»ıåħĥ
    -0.06
    ampa
    -0.06
    storm
    -0.06
    POSITIVE LOGITS
    å¹²æ¶ī
    0.10
    æµ®çĶŁ
    0.08
     interference
    0.08
    inos
    0.08
     }//
    0.07
    Viewer
    0.07
    ocus
    0.07
     Viewer
    0.07
     shimmer
    0.07
    å¸Ī表
    0.07
    Activations Density 0.014%

    No Known Activations