© 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. 43334
    Prev
    Next
    INDEX
    Explanations

    likely modalities and frequency adverbs

    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
     probably
    -0.10
     maybe
    -0.09
     possibly
    -0.09
     presumably
    -0.08
    å±¥è¡ĮèģĮè´£
    -0.08
    åı¯èĥ½åŃĺåľ¨
    -0.08
    åı¯èĥ½æľī
    -0.08
    åĹ£
    -0.08
    åı¯èĥ½çļĦ
    -0.08
    probably
    -0.07
    POSITIVE LOGITS
    mals
    0.08
    çĶļèĩ³æ¯Ķ
    0.08
     sogar
    0.08
    OLI
    0.07
    esch
    0.07
    rasil
    0.07
    çĶļèĩ³ä¼ļ
    0.07
    zet
    0.07
    ollar
    0.07
    çĶļèĩ³æĺ¯
    0.07
    Activations Density 0.124%

    No Known Activations