© 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. 13065
    Prev
    Next
    INDEX
    Explanations

    questionsshowing

    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
    utzen
    -0.07
    ucci
    -0.07
    ä¸įäºī
    -0.07
    ä¸įæĶ¹
    -0.07
    èĢĥè¯ķåĨħ容
    -0.07
    Wür
    -0.07
    erval
    -0.07
    èĩªæĪIJ
    -0.07
    åĪ©äºİ
    -0.06
    çĶ¨è¯Ń
    -0.06
    POSITIVE LOGITS
    æĸ¹æ³ķä¸İ
    0.08
    èħ
    0.08
     methods
    0.08
    methods
    0.08
    rete
    0.07
     juh
    0.07
    Ø¢Ùħ
    0.07
    æĸ¹æ³ķæĿ¥
    0.07
     Methods
    0.07
    êng
    0.07
    Activations Density 0.097%

    No Known Activations