© 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. 42814
    Prev
    Next
    INDEX
    Explanations

    energy levels and metrics

    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
    ansa
    -0.08
    æ°´éĩı
    -0.08
    稳
    -0.07
     infil
    -0.07
    .splice
    -0.06
     Narc
    -0.06
    urry
    -0.06
    ä¸ļåĬ¡èĮĥåĽ´
    -0.06
    OPS
    -0.06
    人æķ°
    -0.06
    POSITIVE LOGITS
    elden
    0.08
     gá»ijc
    0.07
    åŀĴ
    0.07
    åħĥèĩ³
    0.07
    çĥŃèĥ½
    0.07
    ига
    0.07
    Bloc
    0.07
    kof
    0.07
    indung
    0.07
     discomfort
    0.07
    Activations Density 0.002%

    No Known Activations