© 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. 9534
    Prev
    Next
    INDEX
    Explanations

    repressed, congestion, buried, stuffed

    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
    opak
    -0.08
    輩
    -0.07
    幻影
    -0.07
    æľīæķĪæľŁèĩ³
    -0.07
     vanh
    -0.07
    mater
    -0.07
    æ¶īæ°´
    -0.07
    plash
    -0.07
    inst
    -0.07
    ston
    -0.07
    POSITIVE LOGITS
    éĥģ
    0.10
    éĹ·
    0.09
    éĺ»å¡ŀ
    0.09
     lâu
    0.09
    å¾Ĺä¸įåĪ°
    0.08
    ä¹ħèĢĮ
    0.08
    ä¸įçķħ
    0.08
    æĤ¶
    0.08
    ä¸įæķ£
    0.08
    uzzi
    0.08
    Activations Density 0.004%

    No Known Activations