© 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. 23158
    Prev
    Next
    INDEX
    Explanations

    plaque assay, scholarship, Google Spreadsheet

    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
    -0.08
    Äı
    -0.07
    çī¹å°Ķ
    -0.07
    awat
    -0.07
    anus
    -0.07
    imately
    -0.07
    tures
    -0.07
    åĴĮæĶ¿åºľ
    -0.07
    IMATE
    -0.06
    éľ²å¤´
    -0.06
    POSITIVE LOGITS
     '..',
    0.07
    indest
    0.07
    GEST
    0.06
     Tick
    0.06
    å¯Ĵ
    0.06
    é£ĵé£İ
    0.06
    åıĭ们
    0.06
    bury
    0.06
    ستÙĬ
    0.06
    ething
    0.06
    Activations Density 1.571%

    No Known Activations