© 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. 11462
    Prev
    Next
    INDEX
    Explanations

    word formation and linguistic features

    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
    ech
    -0.07
    nod
    -0.07
    egna
    -0.07
    ellini
    -0.07
    幻影
    -0.06
     fluid
    -0.06
    accia
    -0.06
    è·¡
    -0.06
    æ³¢åĬ¨
    -0.06
    Fluid
    -0.06
    POSITIVE LOGITS
    uffix
    0.08
     Corpus
    0.08
     ترÙĥÙĬب
    0.08
     compos
    0.08
     infix
    0.08
     composé
    0.07
     prefixes
    0.07
    refix
    0.07
     dér
    0.07
    ç»Ħè¯į
    0.07
    Activations Density 0.011%

    No Known Activations