© 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. 18621
    Prev
    Next
    INDEX
    Explanations

    dipyridines, pyrimidines, or phosphine oxides

    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
    ewnÄĻ
    -0.08
    éĤ¸
    -0.07
    ä¸ĢæŃ¥
    -0.07
    åįĬæŃ¥
    -0.07
    rg
    -0.07
    ardless
    -0.07
    ä¸īäºĶ
    -0.07
    soever
    -0.07
    åĩłæŃ¥
    -0.07
    ungsweise
    -0.07
    POSITIVE LOGITS
    æĪĸå¤ļ
    0.10
    åĴĮä¸ī
    0.09
    èĴĻå¾·
    0.08
    onis
    0.07
    ées
    0.07
    /single
    0.07
    umb
    0.07
    lach
    0.07
    erty
    0.07
    æł¼å±Ģ
    0.07
    Activations Density 0.062%

    No Known Activations