© 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. 49584
    Prev
    Next
    INDEX
    Explanations

    connectivity and graph structures

    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
    defaults
    -0.07
    tro
    -0.07
    åºķèķ´
    -0.07
    åįĥéĩĮ
    -0.06
    auce
    -0.06
     Subs
    -0.06
     lapse
    -0.06
     z
    -0.06
    vern
    -0.06
    blo
    -0.06
    POSITIVE LOGITS
     connectivity
    0.09
    erto
    0.08
    åħ«æĸ¹
    0.08
    ä¸Ń度
    0.08
    mtree
    0.07
    å¥ĩ
    0.07
     Connectivity
    0.07
    éļıçĿĢå¹´é¾ĦçļĦå¢ŀéķ¿
    0.07
    omes
    0.07
    wd
    0.07
    Activations Density 0.008%

    No Known Activations