© 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. 56235
    Prev
    Next
    INDEX
    Explanations

    firstly, Inductive, PdfP Table

    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
    éĥ½åºĶ该
    -0.08
    ĵĴ
    -0.07
    зка
    -0.07
    izzi
    -0.07
    Ïĥή
    -0.07
    波士顿
    -0.07
    pron
    -0.07
    apar
    -0.07
    oze
    -0.07
    å®ŀå®ŀåľ¨
    -0.07
    POSITIVE LOGITS
    é¦ĸåħĪ
    0.11
     firstly
    0.09
     Firstly
    0.08
    ãģ¾ãģļ
    0.08
    éĩĩçĶ¨
    0.08
    åħĪ
    0.08
    设
    0.07
     first
    0.07
    åģĩ设
    0.07
    é¦ĸåħĪéľĢè¦ģ
    0.07
    Activations Density 0.026%

    No Known Activations