© 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. 20158
    Prev
    Next
    INDEX
    Explanations

    goal, cost, experience, new, possible

    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
    hou
    -0.07
    indow
    -0.07
    quo
    -0.07
    bin
    -0.07
    kat
    -0.07
    kend
    -0.07
    æıIJé«ĺæķĪçİĩ
    -0.07
    çīĽå¸Ĥ
    -0.06
    éŃĶæĹı
    -0.06
    åIJ«æľīçļĦ
    -0.06
    POSITIVE LOGITS
    åľ¨æľ¬æ¬¡
    0.09
     yours
    0.07
     ours
    0.07
    åľ¨æŃ¤æ¬¡
    0.07
    ENN
    0.07
    ocks
    0.07
    ä¸İä¹ĭ
    0.07
     theirs
    0.07
    EXTERN
    0.07
    以æŃ¤ä¸º
    0.07
    Activations Density 0.341%

    No Known Activations