© 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
    2. Qwen3.5-9B Base
    3. 15-QWENSCOPE-RES-64K
    4. 45267
    Prev
    Next
    INDEX
    Explanations

    book, film, comics, game of thrones

    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
    åıijèĩª
    -0.06
     depart
    -0.06
     something
    -0.06
    å±ħçĦ¶
    -0.06
    Ðļи
    -0.06
    Âł
    -0.06
    ↵↵
    -0.05
    ä¸Ģåı£
    -0.05
    uhu
    -0.05
    èĥĮåIJİ
    -0.05
    POSITIVE LOGITS
    åİŁèijĹ
    0.09
     timeline
    0.09
    çķªå¤ĸ
    0.08
    é£İå°ĺ
    0.08
    elas
    0.08
    交代
    0.08
    artal
    0.08
    timeline
    0.08
    åIJİæľŁçļĦ
    0.07
    å§ĭèĩ³
    0.07
    Activations Density 0.173%

    No Known Activations