© 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. 51265
    Prev
    Next
    INDEX
    Explanations

    academic excellence

    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
    å¾Ħ
    -0.07
    egna
    -0.07
    ugia
    -0.07
     thức
    -0.06
    лома
    -0.06
    åħ°åį¡
    -0.06
    elling
    -0.06
    ives
    -0.06
    erty
    -0.06
    ä»ĺ
    -0.06
    POSITIVE LOGITS
     [&
    0.07
    æĬķèµĦæĪĸ
    0.07
    å¹³åı°åĴĮ
    0.06
    ರಿ
    0.06
    人è´Ńä¹°
    0.06
    rama
    0.06
    mittag
    0.06
     Yol
    0.06
     Postar
    0.06
    ssen
    0.06
    Activations Density 0.303%

    No Known Activations