© 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. 32801
    Prev
    Next
    INDEX
    Explanations

    sources of information and authority

    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
    èĢĮ被
    -0.09
    è¦ģ被
    -0.09
    è¢«ä¾ĽåºĶåķĨ
    -0.09
    并æĪIJ为
    -0.09
    åıĪ被
    -0.08
    ä¸įèĥ½è¢«
    -0.08
    被人
    -0.08
    åľ°è¢«
    -0.08
    è¢«ä½ł
    -0.08
    åı¯ä»¥è¢«
    -0.08
    POSITIVE LOGITS
    对æѤ
    0.11
    å°Ĩåħ¶
    0.10
    å°Ĩè¿Ļ个
    0.09
    åįģåĪĨéĩįè§Ĩ
    0.09
    å°ĨæѤ
    0.09
     uses
    0.09
    å°Ĩå®ĥ
    0.08
    æĬĬè¿Ļ个
    0.08
    éĿŀ常éĩįè§Ĩ
    0.08
     assumes
    0.08
    Activations Density 0.239%

    No Known Activations