© 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. 14735
    Prev
    Next
    INDEX
    Explanations

    appointed or hiring someone/something

    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
    anger
    -0.07
    mailer
    -0.07
    æĺ¯åŃ©åŃIJ
    -0.06
    anda
    -0.06
    arer
    -0.06
    walker
    -0.06
    ÙĪص
    -0.06
    æĺ¯åѦçĶŁ
    -0.06
    åѦéķ¿
    -0.06
    主人çļĦ
    -0.06
    POSITIVE LOGITS
    äºĨä¸Ģæī¹
    0.09
     diri
    0.09
    /lic
    0.09
    人åijĺè¿Ľè¡Į
    0.08
    äºĨä¸Ģ个
    0.08
    /dis
    0.08
    ä¸ĵäººè´Łè´£
    0.08
     лÑĥÑĩÑĪего
    0.08
    äºĨä¸Ģä½į
    0.07
    å¾ĹåĬĽ
    0.07
    Activations Density 0.156%

    No Known Activations