© 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. 32733
    Prev
    Next
    INDEX
    Explanations

    chromatography and exchange

    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
    çĩĥ
    -0.09
    éĽĨæĪIJçģ¶
    -0.07
    íĴĢ
    -0.07
    çĩĥæ°Ķ
    -0.07
    ihu
    -0.07
     combustion
    -0.07
    çĦļ
    -0.07
    etem
    -0.07
    çģ«çĤī
    -0.07
    iff
    -0.06
    POSITIVE LOGITS
    åIJ¸éĻĦ
    0.09
    éģİ濾
    0.08
    .Filter
    0.08
    (filters
    0.08
     filter
    0.08
    è¿ĩ滤
    0.08
    filter
    0.08
    Filter
    0.08
    /filter
    0.08
     filters
    0.08
    Activations Density 0.116%

    No Known Activations