© 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. 48934
    Prev
    Next
    INDEX
    Explanations

    crystal structure resolution

    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
    ãĥĨãĤ¹ãĥĪ
    -0.07
    æµĭè¯ķ
    -0.07
    æµĭè¯ķç»ĵæŀľ
    -0.07
    åı£çļĦ
    -0.07
     fart
    -0.07
    åIJĬ
    -0.07
    ä½Ĩåıªè¦ģ
    -0.07
    Testing
    -0.07
    æłĩçļĦ
    -0.06
    è¿Ľè¡Įæµĭè¯ķ
    -0.06
    POSITIVE LOGITS
     elucid
    0.10
    pdb
    0.09
     Candid
    0.09
     snapshots
    0.09
     ensam
    0.08
     assembled
    0.08
     ì°į
    0.08
     decipher
    0.08
     crystal
    0.08
     Cristal
    0.08
    Activations Density 0.113%

    No Known Activations