© 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. 26559
    Prev
    Next
    INDEX
    Explanations

    names and abbreviations after punctuation

    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
    avera
    -0.08
    íĴį
    -0.07
    Rub
    -0.07
    indah
    -0.07
    pire
    -0.07
    ves
    -0.07
    åĨĬ
    -0.07
    ivio
    -0.07
    ibal
    -0.07
    èº
    -0.07
    POSITIVE LOGITS
    äºĭæĪIJ
    0.08
    Ø´ÙĨ
    0.07
    lsi
    0.06
     Farage
    0.06
     lu
    0.06
    æİĮ
    0.06
    çģ«çĤ¬
    0.06
     wacht
    0.06
    ominated
    0.06
     ::=
    0.06
    Activations Density 0.053%

    No Known Activations