© 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. 51161
    Prev
    Next
    INDEX
    Explanations

    chrome=1

    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
    olik
    -0.09
    alink
    -0.08
    tagon
    -0.08
    adang
    -0.08
    è¿Ľä¸ĢæŃ¥è§ĦèĮĥ
    -0.08
    ió
    -0.08
    ély
    -0.08
    ãĥ¼ãĥ¼ãĥ¼ãĥ¼ãĥ¼ãĥ¼ãĥ¼ãĥ¼
    -0.08
    etet
    -0.08
    ÑĤелÑĮ
    -0.07
    POSITIVE LOGITS
    >=
    0.07
    umo
    0.06
     preferably
    0.06
    èĩ³å°ij
    0.06
    ç¡®ä¿Ŀ
    0.06
    æĿİå°ı
    0.06
     confines
    0.06
    Since
    0.06
     Ens
    0.06
    prefer
    0.06
    Activations Density 0.027%

    No Known Activations