© 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. 38141
    Prev
    Next
    INDEX
    Explanations

    Retrieved date

    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
    带好
    -0.09
    egna
    -0.08
    usst
    -0.08
    igni
    -0.08
    enco
    -0.08
    inati
    -0.08
    ftime
    -0.08
    ICODE
    -0.08
    abouts
    -0.07
    åĮĹéĿ¢
    -0.07
    POSITIVE LOGITS
     https
    0.06
     ISSN
    0.06
    ulum
    0.06
    _targets
    0.06
    åĭĴæĸ¯
    0.06
    æĪĺ线
    0.06
    à¹Ħมà¹Īà¸Ļà¹īà¸Ńย
    0.06
    ä¸įäºĨçļĦ
    0.05
    zer
    0.05
    :
    0.05
    Activations Density 0.401%

    No Known Activations