© 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. 2260
    Prev
    Next
    INDEX
    Explanations

    seeking to save

    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
    èĤ²æĪIJ
    -0.08
    ixa
    -0.08
    boom
    -0.08
    羣æĬĵ
    -0.08
     reliably
    -0.08
    .der
    -0.07
    èĬ®
    -0.07
     panen
    -0.07
    ¤íŀ
    -0.07
    ä¸½å¨ľ
    -0.07
    POSITIVE LOGITS
     seeks
    0.08
    尽快
    0.08
    -seeking
    0.07
    寻æ±Ĥ
    0.07
    å°½éĩıåĩıå°ij
    0.07
     seek
    0.07
    èĪĴæľį
    0.07
     strive
    0.07
    èĪĴæľįçļĦ
    0.07
     strives
    0.07
    Activations Density 0.041%

    No Known Activations