© 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. 21384
    Prev
    Next
    INDEX
    Explanations

    N-containing chemical compounds

    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
    翼翼
    -0.08
    çıij
    -0.07
    çĶŁç´ł
    -0.07
    ÑĤли
    -0.07
    elm
    -0.07
    é²ľæ´»
    -0.07
    etÅij
    -0.07
    ailable
    -0.07
    angeb
    -0.07
    cky
    -0.07
    POSITIVE LOGITS
    atters
    0.07
    仲
    0.07
    妾
    0.07
    çļĦèį¯çī©
    0.07
    ayne
    0.07
     donor
    0.07
    è±ļ
    0.07
    ounge
    0.07
    ä¸½å¨ľ
    0.07
     transfers
    0.06
    Activations Density 0.075%

    No Known Activations