© 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. 4171
    Prev
    Next
    INDEX
    Explanations

    charge transfer and accumulated charge

    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
    çīµ
    -0.07
     multid
    -0.07
    æĶ¾æħ¢
    -0.07
    ëĸ¨
    -0.07
    abbr
    -0.07
    _convert
    -0.07
    éĺģä¸ĭ
    -0.07
    è¯ĦéĢī
    -0.06
    éĹĬ
    -0.06
    æĬĺæī£
    -0.06
    POSITIVE LOGITS
    èį·
    0.08
     redistributed
    0.08
    æĢ»éĩı
    0.08
    驱使
    0.08
     distributed
    0.08
    æĢ»é¢Ŀ
    0.08
    комплек
    0.08
    æĢ»éĩıçļĦ
    0.07
     manifests
    0.07
     charges
    0.07
    Activations Density 0.001%

    No Known Activations