© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 44370
    Prev
    Next
    INDEX
    Explanations

    closing punctuation or brackets

    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
    Negative Logits
    ibase
    -0.08
    ember
    -0.07
    èļģ
    -0.07
    å¿ĥçĶĺ
    -0.07
    æ°Ľ
    -0.07
    andom
    -0.07
    aled
    -0.06
    stor
    -0.06
    let
    -0.06
    ffffffff
    -0.06
    POSITIVE LOGITS
    OLI
    0.07
    -zA
    0.07
    estic
    0.07
    дове
    0.07
    OPSIS
    0.07
    omini
    0.07
    å±ķå¼Ģåħ¨éĥ¨
    0.07
    ehme
    0.07
    æĬĬä»ĸ们
    0.07
    ienti
    0.07
    Activations Density 0.107%

    No Known Activations