© 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. 45124
    Prev
    Next
    INDEX
    Explanations

    within the

    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
    ç¯Ŀ
    -0.07
    å·¥ä¸ļåĮĸ
    -0.07
    åīįåIJİ
    -0.07
    éĩįéĩı
    -0.06
     ÑģÑĤиÑħ
    -0.06
    æĪĸå¤ļæĪĸå°ij
    -0.06
    éĩıåĴĮ
    -0.06
    å®ĮäºĨ
    -0.06
    æ·»
    -0.06
     signed
    -0.06
    POSITIVE LOGITS
    鼷å°Ħ
    0.09
    _UNIQUE
    0.09
    бÑĢи
    0.08
    /native
    0.08
    æĬĺå°Ħ
    0.08
    ãĤ®ãĥª
    0.08
    临çķĮ
    0.08
    ulp
    0.08
    -divider
    0.08
    æŀģéĻIJ
    0.08
    Activations Density 0.001%

    No Known Activations