© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 20812
    Prev
    Next
    INDEX
    Explanations

    elements and compounds containing them

    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
    /rem
    -0.07
    éĺŁä¼į
    -0.07
    issa
    -0.07
    åĴĮåIJĪä½ľ
    -0.07
    æĪĸ被
    -0.06
    nie
    -0.06
    statt
    -0.06
    åĿĽ
    -0.06
    igh
    -0.06
    éĺŁ
    -0.06
    POSITIVE LOGITS
    -containing
    0.11
    -rich
    0.10
    -bearing
    0.09
    loch
    0.09
     prezi
    0.08
    ä»ħ次äºİ
    0.08
    åħĥç´łçļĦ
    0.08
    -scrollbar
    0.08
    第äºĮ大
    0.08
    å¦ĤèĬ±
    0.08
    Activations Density 0.089%

    No Known Activations