© 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. 39898
    Prev
    Next
    INDEX
    Explanations

    marginal, incremental costs, utility, revenue

    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
    etro
    -0.08
     Fatal
    -0.08
    istrz
    -0.07
    etra
    -0.07
    èĩ¼
    -0.07
    ontre
    -0.07
    íĭĢ
    -0.07
    ((__
    -0.07
    åį§é¾Ļ
    -0.07
    tram
    -0.07
    POSITIVE LOGITS
    è¾¹éĻħ
    0.08
    shed
    0.08
     infinit
    0.08
    éĢĴåĩı
    0.07
    æĽ²
    0.07
    avadoc
    0.07
    éĢĴ
    0.07
    çī©èģĶ
    0.07
     incremental
    0.07
    åĪ»çĶ»
    0.07
    Activations Density 0.001%

    No Known Activations