© 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. 55405
    Prev
    Next
    INDEX
    Explanations

    invasive species

    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
     mood
    -0.07
    dirty
    -0.06
    antina
    -0.06
    åĬ³éĢ¸
    -0.06
    å¾Ģ常ä¸Ģæł·
    -0.06
    addin
    -0.06
     ala
    -0.06
    umber
    -0.06
    æĶĴ
    -0.06
    antin
    -0.06
    POSITIVE LOGITS
     invasive
    0.10
    ç¹ģæ®ĸ
    0.10
    à¸ŀัà¸Ļà¸ĺุà¹Į
    0.09
    åIJįå½ķ
    0.09
    vasive
    0.09
    óta
    0.08
    çī©ç§į
    0.08
     monoc
    0.08
    æľ¬åľŁ
    0.08
    -native
    0.08
    Activations Density 0.046%

    No Known Activations