© 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. 1673
    Prev
    Next
    INDEX
    Explanations

    energy, stability, bonds

    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
    ä¸įéĻIJ
    -0.08
    é£İåIJij
    -0.08
    terer
    -0.08
    æ±°
    -0.07
    许æĦ¿
    -0.07
    andr
    -0.07
    patial
    -0.07
    ä¼łäºº
    -0.07
    croft
    -0.07
    ä¸ĵåĪ©
    -0.07
    POSITIVE LOGITS
     bonds
    0.08
     cohesion
    0.08
    åĩĿèģļåĬĽ
    0.08
    ãĤ»ãĤŃãĥ¥
    0.07
     bonding
    0.07
    æīĵè¿Ľ
    0.07
    omer
    0.07
     bond
    0.07
     Tab
    0.07
    çļĦæ¦Ĥ念
    0.07
    Activations Density 0.001%

    No Known Activations