© 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. 45770
    Prev
    Next
    INDEX
    Explanations

    medical graduates and general practice training

    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
    rylic
    -0.07
    marvin
    -0.07
    å¹´åįĬ
    -0.07
    akor
    -0.07
    Õ¡Õ£
    -0.07
    onia
    -0.07
    ä¹ĭ忧
    -0.07
     repl
    -0.07
    Åijs
    -0.06
     reim
    -0.06
    POSITIVE LOGITS
    ç®Ģ称
    0.15
    (SC
    0.14
    (SS
    0.13
     abbreviated
    0.12
    (PC
    0.12
    (DB
    0.12
    簡稱
    0.11
    (OS
    0.11
    缩åĨĻ
    0.11
    以ä¸ĭç®Ģ称
    0.11
    Activations Density 3.472%

    No Known Activations