© 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. 57604
    Prev
    Next
    INDEX
    Explanations

    chemical substituents and 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
    éĢļè¿ĩ使çĶ¨
    -0.07
    ere
    -0.07
    èĩªæĪIJ
    -0.07
    .snapshot
    -0.06
    ä¸įå¼ĥ
    -0.06
    ĶĦ
    -0.06
    åĩºèº«çļĦ
    -0.06
    解ä½ĵ
    -0.06
    丹éĿĴ
    -0.06
    ITH
    -0.06
    POSITIVE LOGITS
    åĪĨå¸ĥåľ¨
    0.09
    ä½įäºİ
    0.09
    åĪĨå¸ĥäºİ
    0.08
    åıijçİ°åľ¨
    0.08
    ä½įæĸ¼
    0.08
    apore
    0.07
     positioned
    0.07
     Strateg
    0.07
    åį«ä¸ľ
    0.07
    åĪĨå¸ĥ
    0.07
    Activations Density 0.042%

    No Known Activations