© 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. 38688
    Prev
    Next
    INDEX
    Explanations

    discussing ethics and news articles

    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
    ecker
    -0.07
    äºĶ大
    -0.07
    ampionship
    -0.07
    halen
    -0.07
    ниÑĨÑĥ
    -0.07
    æģ°
    -0.06
    abei
    -0.06
     fanta
    -0.06
    ulus
    -0.06
    çī¹æľī
    -0.06
    POSITIVE LOGITS
    prog
    0.08
    ç»Ļæľĭåıĭ
    0.08
    enville
    0.07
    zan
    0.07
    trz
    0.07
    æĻ®ç½Ĺ
    0.07
    resher
    0.07
    é¢ĺ
    0.07
    ersh
    0.07
    大å±ķ
    0.07
    Activations Density 0.066%

    No Known Activations