© 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. 37893
    Prev
    Next
    INDEX
    Explanations

    transcending concepts

    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
    izia
    -0.09
    hausen
    -0.09
    Äija
    -0.09
    баланÑģи
    -0.08
    íĥģ
    -0.08
    大æĪIJ
    -0.08
    -ok
    -0.08
    ENTOS
    -0.08
    urunk
    -0.08
    çīĩåŃIJ
    -0.08
    POSITIVE LOGITS
    æĢ§çļĦ
    0.09
    èĦ±ä¿Ĺ
    0.08
    è¶ħè¶Ĭ
    0.08
     khá»ıi
    0.08
     beyond
    0.08
    æĢ§åľ°
    0.08
     transc
    0.08
    级çļĦ
    0.08
    ental
    0.07
    äºĨçļĦ
    0.07
    Activations Density 0.007%

    No Known Activations