© 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. 30046
    Prev
    Next
    INDEX
    Explanations

    kilodalton, Dalton, Da

    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
    lak
    -0.08
    oran
    -0.07
    ×ķתר
    -0.07
    ãĥĦãĤ¤
    -0.07
    irst
    -0.07
    åıĤä¸İè¯Ħ论
    -0.07
    çĶ¨å¿ĥåİ»
    -0.07
    otra
    -0.07
    æł¼å°Ķ
    -0.07
    obox
    -0.07
    POSITIVE LOGITS
    wiss
    0.08
     اÙĦÙĪاØŃد
    0.07
    quiv
    0.07
    ç¢İ
    0.07
     karÅŁ
    0.07
    ç©Ģ
    0.07
    åı©
    0.06
    indelijk
    0.06
    quirer
    0.06
    ivet
    0.06
    Activations Density 0.003%

    No Known Activations