© 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. 17570
    Prev
    Next
    INDEX
    Explanations

    its, the, prior, Open, FS

    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
    eras
    -0.07
    etra
    -0.07
    asco
    -0.07
    nai
    -0.06
    fact
    -0.06
    uez
    -0.06
    cky
    -0.06
    inja
    -0.06
    æ´ĭ
    -0.06
    acon
    -0.06
    POSITIVE LOGITS
    обе
    0.07
     appunto
    0.07
    chos
    0.07
    еÑģе
    0.07
     whichever
    0.07
    Ú¯ÙĪÙĨ
    0.07
    çĶļèĩ³æĺ¯
    0.07
    åIJĦèĩªçļĦ
    0.07
    ä¹ĥèĩ³
    0.06
    åĪĩå®ŀæĬĬ
    0.06
    Activations Density 0.016%

    No Known Activations