© 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. 975
    Prev
    Next
    INDEX
    Explanations

    triple bond or concerto

    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
    æ·ĺ
    -0.09
    ä¸įæĭĶ
    -0.08
    acce
    -0.08
     tama
    -0.07
     Tum
    -0.07
    æľ¬èī²
    -0.07
     Erm
    -0.07
    abee
    -0.07
     tum
    -0.07
    ske
    -0.07
    POSITIVE LOGITS
    æĪĸå°ij
    0.09
    /high
    0.08
    ç¾²
    0.07
    FormatException
    0.07
    åĮĸåIJĪ
    0.07
     shorthand
    0.07
    atron
    0.07
     sparing
    0.07
    äº¤æĽ¿
    0.07
    .insertBefore
    0.06
    Activations Density 0.002%

    No Known Activations