© 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. 30424
    Prev
    Next
    INDEX
    Explanations

    Alaska

    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
    ools
    -0.06
    åįĥ
    -0.06
    REN
    -0.06
    ç®Ĺ
    -0.06
    Sector
    -0.06
    anken
    -0.05
    èIJ½åľ¨äºĨ
    -0.05
    ARA
    -0.05
     Parker
    -0.05
    çļĦçĶŁåij½
    -0.05
    POSITIVE LOGITS
    ãģĵãģ¡ãĤīãĤĤ
    0.11
    ãģĵãĤĮãĤĤ
    0.10
     Again
    0.09
     again
    0.09
    again
    0.09
    #index
    0.09
    åıĪæĺ¯ä¸Ģ个
    0.08
    åIJĮæł·æĺ¯
    0.08
    Again
    0.08
    åıĪä¸Ģ个
    0.08
    Activations Density 0.351%

    No Known Activations