© 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. 40761
    Prev
    Next
    INDEX
    Explanations

    connection and continuation

    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
     somewhat
    -0.09
    åīįè¿°
    -0.09
    éĿŀ常好çļĦ
    -0.08
     _
    -0.08
     thereof
    -0.07
    æŁIJç§į
    -0.07
    è¾ĥ为
    -0.07
    è¾ĥ好çļĦ
    -0.07
     whence
    -0.07
     roughly
    -0.07
    POSITIVE LOGITS
     your
    0.12
     effortlessly
    0.12
    **!
    0.11
    your
    0.11
     yourself
    0.11
     yours
    0.10
    åĴĮä½łçļĦ
    0.10
     guaranteed
    0.10
    -your
    0.10
    !**
    0.10
    Activations Density 2.649%

    No Known Activations