© 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. 2416
    Prev
    Next
    INDEX
    Explanations

    mathematical derivatives and expressions

    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
    åīįèĮħ
    -0.08
    sher
    -0.08
    queo
    -0.08
    èłķ
    -0.07
    æ²¹æĢ§
    -0.07
    ç«¥åŃIJ
    -0.07
    ç»ĦåĽ¢
    -0.07
    {'
    -0.07
    æĸĩåĵ²
    -0.07
    .ev
    -0.07
    POSITIVE LOGITS
    ¥
    0.06
    obble
    0.06
    ung
    0.06
     tele
    0.06
    åľ°æĬĬ
    0.06
    umb
    0.06
    ìłķ
    0.06
    åıĪæĬĬ
    0.06
    atalog
    0.06
    andra
    0.06
    Activations Density 0.003%

    No Known Activations