© 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. 47721
    Prev
    Next
    INDEX
    Explanations

    imidazolium and oxadiazole chemical structures

    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
    iad
    -0.09
    \Php
    -0.08
    åģĩå±±
    -0.08
    tings
    -0.08
    æĩĴå¾Ĺ
    -0.08
    妥å½ĵ
    -0.08
    inition
    -0.07
    æ°´åĻ¨
    -0.07
    zers
    -0.07
    enson
    -0.07
    POSITIVE LOGITS
    abor
    0.08
    åĸĥ
    0.07
    -based
    0.07
    plain
    0.06
    åĴķ
    0.06
    idi
    0.06
    uitar
    0.06
    egral
    0.06
    istian
    0.06
     creation
    0.06
    Activations Density 0.049%

    No Known Activations