© 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. 17520
    Prev
    Next
    INDEX
    Explanations

    bibliography references or code snippets

    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
    ish
    -0.08
    åĨħ容æıIJä¾Ľæĸ¹
    -0.08
    /{$
    -0.07
    ä¼ģä¸ļæŁ¥è¯¢
    -0.07
    itic
    -0.07
    ä¸Ģè¨Ģ
    -0.07
    az
    -0.07
    çĻ»å½ķåIJİæŁ¥çľĭ
    -0.07
    ës
    -0.07
    ¬¸
    -0.07
    POSITIVE LOGITS
    reno
    0.07
    äºĶæĺŁçº§
    0.06
    kota
    0.06
    паÑģ
    0.06
    æĿ¡æĿ¡
    0.06
    æ´ĭ溢
    0.06
    æĺ¯è¿Ļæł·çļĦ
    0.06
    _PROTO
    0.06
    æį®æѤ
    0.06
    èĢĮ导èĩ´
    0.06
    Activations Density 0.050%

    No Known Activations