© 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. 11630
    Prev
    Next
    INDEX
    Explanations

    keywords in programming and math

    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
     fragment
    -0.06
    å¯Į
    -0.06
     tr
    -0.06
    erci
    -0.06
    åij¼å£°
    -0.06
    寡
    -0.06
    沧
    -0.06
     Rau
    -0.05
    ater
    -0.05
     disproportion
    -0.05
    POSITIVE LOGITS
    veen
    0.09
    å¤ĩå¿ĺ
    0.08
    uve
    0.08
    æľīåħ³è¦ģæ±Ĥ
    0.08
    ç»İ
    0.08
    .nb
    0.08
    çļĦåĮºåĪ«
    0.08
    ppe
    0.08
    åĮºåĪ«
    0.08
    ãģĵãģ¡ãĤīãģ¯
    0.08
    Activations Density 0.026%

    No Known Activations