© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 48478
    Prev
    Next
    INDEX
    Explanations

    symbolic math and code tokens

    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
    读åį¡
    -0.09
    å°ıå¹³
    -0.08
    è¿ĽéĢĢ
    -0.07
    mens
    -0.07
    ikum
    -0.07
    arvi
    -0.07
    æĺ¯å°ı
    -0.07
    娱
    -0.07
    æīĭæĦŁ
    -0.07
    çī¹åĪ«å£°æĺİ
    -0.07
    POSITIVE LOGITS
    æ²īæ²ī
    0.08
    flow
    0.07
    assen
    0.07
    ç«ĭãģ¡
    0.07
    vo
    0.07
    æĺıæĺı
    0.06
    voz
    0.06
    æĪijçļĦ家乡
    0.06
    _REST
    0.06
    _extraction
    0.06
    Activations Density 0.002%

    No Known Activations