© 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. 4541
    Prev
    Next
    INDEX
    Explanations

    want is / saw it / left it

    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
     whose
    -0.07
     którego
    -0.07
     somehow
    -0.06
    æľīä¸Ģå¥Ĺ
    -0.06
     something
    -0.06
    ä»Ģä¹Īåij¢
    -0.06
    something
    -0.06
    çľĭäºĨ
    -0.06
     accordingly
    -0.06
    äºĨåIJĹ
    -0.06
    POSITIVE LOGITS
    çľĭå¾ħ
    0.11
    以åıĬå¦Ĥä½ķ
    0.11
     ÙĪÙĥÙĬÙģ
    0.10
    对å¾ħ
    0.09
    çļĦéĤ£æł·
    0.09
    æģ©æĸ¯
    0.08
    vey
    0.08
     réellement
    0.08
     eigentlich
    0.08
     effettivamente
    0.08
    Activations Density 0.423%

    No Known Activations