© 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. 25668
    Prev
    Next
    INDEX
    Explanations

    territory, frequency, females, curve, units, flows

    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
     >::
    -0.08
    æĹ
    -0.07
    Agence
    -0.07
    ëĿ¼ëıĦ
    -0.07
    ä¿ĥè¿Ľä¼ļ
    -0.07
    åĨįä¸Ĭæĸ°åı°éĺ¶
    -0.07
    езде
    -0.07
    ละ
    -0.07
    urah
    -0.07
    ש×ij
    -0.07
    POSITIVE LOGITS
    nen
    0.07
     itulah
    0.07
    ä¹Łç§°ä¸º
    0.06
    ãĤıãģijãģ§
    0.06
    æīĢ以说
    0.06
     eventually
    0.06
    å®ŀéĻħä¸Ĭ
    0.06
    æīį被
    0.06
    å¦Ĥæŀľä½ł
    0.06
    亮çļĦ
    0.06
    Activations Density 0.021%

    No Known Activations