© 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. 14075
    Prev
    Next
    INDEX
    Explanations

    improvement or getting better

    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
    stan
    -0.09
    ãģ¾ãģ¾
    -0.08
    æĪĸå°ij
    -0.08
    новениÑı
    -0.08
    ness
    -0.08
    ueb
    -0.07
    à§Ģয়
    -0.07
    знание
    -0.07
    cribe
    -0.07
    arella
    -0.07
    POSITIVE LOGITS
    åĴĮæĶ¹è¿Ľ
    0.11
    æĹłæŃ¢å¢ĥ
    0.10
    åĴĮä¼ĺåĮĸ
    0.10
    åĴĮæıIJé«ĺ
    0.10
    åĴĮæĶ¹åĸĦ
    0.10
    åĴĮå®ĮåĸĦ
    0.09
    åĴĮæıIJåįĩ
    0.09
    /up
    0.09
    ments
    0.08
    /ref
    0.08
    Activations Density 0.092%

    No Known Activations