© 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. 38833
    Prev
    Next
    INDEX
    Explanations

    equations with variables

    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
    ices
    -0.07
    ึà¸ģ
    -0.07
    onton
    -0.07
    miss
    -0.06
    ÛĮØ´
    -0.06
    æѦè£ħ
    -0.06
    åIJĬ
    -0.06
    éħ¸
    -0.06
    ä»»
    -0.06
    çĭŃ
    -0.06
    POSITIVE LOGITS
     pär
    0.10
    idro
    0.08
    =?,
    0.07
    åŀ£
    0.07
    obil
    0.07
    èĭį天
    0.07
    æĦŁåįģ足
    0.07
    æ²ŁéĢļåįıè°ĥ
    0.07
    èĢģåŁİ
    0.07
    atsu
    0.07
    Activations Density 0.017%

    No Known Activations