© 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. 11197
    Prev
    Next
    INDEX
    Explanations

    control device

    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
    åį³åĪ°
    -0.09
    çĨŁçŁ¥
    -0.08
    éĽĢ
    -0.08
    alle
    -0.08
    ศรี
    -0.08
    ial
    -0.08
    åĭĴæĸ¯
    -0.08
    acus
    -0.07
    allet
    -0.07
    æľĪåĪ°
    -0.07
    POSITIVE LOGITS
     عÙĦÙĬÙĨا
    0.09
     on
    0.09
     عÙĦÙĬÙĥ
    0.08
     عÙĦÙĬÙĩا
    0.08
    æľ¬åľºæ¯ĶèµĽ
    0.07
     darauf
    0.07
    usercontent
    0.07
    etni
    0.07
     عÙĦÙĬÙĥÙħ
    0.07
    onado
    0.06
    Activations Density 0.018%

    No Known Activations