© 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. 17781
    Prev
    Next
    INDEX
    Explanations

    potential risks, benefits, importance, utility

    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
    #__
    -0.08
    åĬĽæ±Ĥ
    -0.08
    enso
    -0.08
    -validator
    -0.08
    etail
    -0.07
    à¹Ģวียà¸Ļ
    -0.07
    antal
    -0.07
    elic
    -0.07
    eenth
    -0.07
    å¾Ģå¾Ģ
    -0.07
    POSITIVE LOGITS
    entially
    0.12
     future
    0.10
    ëį°ìļĶ
    0.09
    åĪ°çļĦ
    0.09
    ellas
    0.08
    æ½ľåľ¨
    0.08
     harm
    0.08
    æ½ľåľ¨çļĦ
    0.08
    ä¸įå¦Ļ
    0.08
     pitfalls
    0.08
    Activations Density 0.059%

    No Known Activations