© 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. 11877
    Prev
    Next
    INDEX
    Explanations

    PCR tests, wind electric, Western Conference, currency pairs, cookies, insidious

    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
    eger
    -0.07
    âĢ¦
    -0.07
    instanc
    -0.06
    olari
    -0.06
     Beri
    -0.06
    สิà¸Ļ
    -0.06
    æī©å±ķèµĦæĸĻ
    -0.06
    ActionPerformed
    -0.06
    âĢ
    -0.06
    é¹ĥ
    -0.06
    POSITIVE LOGITS
     hingegen
    0.08
    istin
    0.08
     ÙħÙĨÙĩÙħا
    0.08
    ÙĦاء
    0.08
    éĶģ
    0.07
    好èĩªå·±çļĦ
    0.07
     prévo
    0.07
    æĽ´æĺ¯
    0.07
     nachdem
    0.07
    åĪĻæĺ¯
    0.07
    Activations Density 0.226%

    No Known Activations