© 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. 38081
    Prev
    Next
    INDEX
    Explanations

    culture by, period in

    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
    epend
    -0.07
     "%"
    -0.07
    etest
    -0.07
    anke
    -0.07
    llib
    -0.07
    æĸ¯åħĭ
    -0.07
    è¯ĨåĪ«åı·
    -0.06
    ewidth
    -0.06
     createAction
    -0.06
    å°Ķ夫
    -0.06
    POSITIVE LOGITS
    以åıĬå¦Ĥä½ķ
    0.10
     ÙĪاÙĦØ°ÙĬ
    0.09
     ÙĪاÙĦتÙĬ
    0.09
    以åıĬ
    0.09
     sowie
    0.08
     ÙĪبÙĬÙĨ
    0.08
    äºĨåij¢
    0.08
    以åıĬåľ¨
    0.07
     oraz
    0.07
    以åıĬ对
    0.07
    Activations Density 0.862%

    No Known Activations