© 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. 21447
    Prev
    Next
    INDEX
    Explanations

    clarity and understandability

    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
    ç¼łç»µ
    -0.08
    è°Īè°Ī
    -0.08
    对å¾ħ
    -0.07
    rane
    -0.07
    表çݰ为
    -0.07
    odes
    -0.07
    è°ĪåĪ°
    -0.07
    åįģä¸īç«ł
    -0.07
    满èħĶ
    -0.07
     поÑįÑĤа
    -0.07
    POSITIVE LOGITS
    辨è¯Ĩ度
    0.13
    辨认
    0.13
     readability
    0.12
     visually
    0.12
    è¯ĨåĪ«
    0.12
     visual
    0.12
    辨è¯Ĩ
    0.11
    ä¸Ģ缮äºĨçĦ¶
    0.11
    éĨĴ缮
    0.11
    ä¸Ģçľ¼
    0.11
    Activations Density 0.170%

    No Known Activations