© 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. 62205
    Prev
    Next
    INDEX
    Explanations

    uranium dioxide

    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
    eree
    -0.08
    çİ
    -0.08
    çĤİ
    -0.07
    æīĭæ³ķ
    -0.07
    æ¤Ĵ
    -0.07
     á»ijc
    -0.07
    èŃ
    -0.07
    abler
    -0.07
    Ùĩ
    -0.07
    ifter
    -0.07
    POSITIVE LOGITS
    åĽ½å®¶åħ¬åĽŃ
    0.08
    uran
    0.07
    assandra
    0.07
     uranium
    0.07
    éĵIJ
    0.07
    _complex
    0.07
     dioxide
    0.07
    æľīæĸ°çļĦ
    0.07
    éĤ¯éĥ¸
    0.07
    enberg
    0.07
    Activations Density 0.004%

    No Known Activations