© 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. 43117
    Prev
    Next
    INDEX
    Explanations

    phenyl- followed by alkynyl or aryl groups

    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
    ë
    -0.07
    ToDate
    -0.06
    øsse
    -0.06
    มัà¸ĩ
    -0.06
    heen
    -0.06
    åĪ°çĽ®åīį
    -0.06
    vien
    -0.06
     Jes
    -0.06
    代人
    -0.06
    (ii
    -0.06
    POSITIVE LOGITS
    olv
    0.08
    ç¥ŀ
    0.07
    arkin
    0.07
    unte
    0.07
    åijĺ
    0.07
     (âĢ¦)
    0.07
    éģ¥
    0.07
    Injected
    0.07
    euse
    0.07
    èĤ¤
    0.06
    Activations Density 0.007%

    No Known Activations