© 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. 49454
    Prev
    Next
    INDEX
    Explanations

    capacity and measurement units

    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
    ìłĪ
    -0.07
    ãģ¥
    -0.07
    isel
    -0.07
    éļ¾æ±Ĥ
    -0.07
    浪费æŶéĹ´
    -0.07
    altungs
    -0.07
    è°·
    -0.07
    èģĺ
    -0.07
    altung
    -0.07
    ãģĹãģĭãģªãģĦ
    -0.07
    POSITIVE LOGITS
     capacity
    0.13
     capacities
    0.13
    å¤ĦçIJĨèĥ½åĬĽ
    0.12
     capability
    0.12
    capacity
    0.11
     Capacity
    0.11
    èĥ½åĬĽ
    0.10
    èĥ½åĬĽåĴĮ
    0.10
     capabilities
    0.10
     capacidad
    0.10
    Activations Density 0.102%

    No Known Activations