© 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. 31992
    Prev
    Next
    INDEX
    Explanations

    activities and uses

    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
     proceeds
    -0.06
    عا
    -0.06
    å½¢å¼ıçļĦ
    -0.06
    INDER
    -0.06
    å½¢æĪIJäºĨä¸Ģ个
    -0.06
     Microsystems
    -0.06
    缴æİ¥
    -0.06
    å·§å¦Ļåľ°
    -0.06
    çĶŁåij½
    -0.06
     spons
    -0.06
    POSITIVE LOGITS
    é¢ijç¹ģçļĦ
    0.09
     environments
    0.08
     повÑģеднев
    0.08
     exige
    0.08
    é¢ijç¹ģ
    0.08
     fréquent
    0.08
    游åĪĥ
    0.08
    è·¯éĢı
    0.08
    ijIJ
    0.08
    anova
    0.08
    Activations Density 0.142%

    No Known Activations