© 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. 30244
    Prev
    Next
    INDEX
    Explanations

    science and technology descriptors

    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
    /
    -0.10
    ãģ©ãģĵãĤį
    -0.08
    äºĮåŃĹ
    -0.08
    åĮĸå¤ĦçIJĨ
    -0.08
    astic
    -0.08
    ish
    -0.08
    ä¹ĭåħī
    -0.08
    -ish
    -0.08
    å±ĤéĿ¢çļĦ
    -0.07
    ville
    -0.07
    POSITIVE LOGITS
    atics
    0.08
    ả
    0.07
    kse
    0.06
    stelling
    0.06
     (*.
    0.06
    à¸Ļี
    0.06
    yle
    0.06
    geving
    0.06
    以åıĬåħ¶ä»ĸ
    0.06
    anton
    0.06
    Activations Density 1.182%

    No Known Activations