© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 26982
    Prev
    Next
    INDEX
    Explanations

    -esque suffixes

    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
    rastructure
    -0.08
    oleh
    -0.08
    irt
    -0.07
    fst
    -0.07
    èŁĨ
    -0.07
    werker
    -0.07
    åĵ¥åįİ
    -0.07
    ofday
    -0.07
    ÙĪÙĬØ©
    -0.07
    ÑĥÑī
    -0.07
    POSITIVE LOGITS
    ian
    0.12
    -like
    0.11
    æ°ı
    0.11
    -style
    0.10
    -ish
    0.10
    -esque
    0.10
    -type
    0.08
    's
    0.08
    lite
    0.08
    /B
    0.08
    Activations Density 0.233%

    No Known Activations