© 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. 11718
    Prev
    Next
    INDEX
    Explanations

    illa Gunell

    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
    erial
    -0.08
     "=",
    -0.07
    ular
    -0.07
     Laurea
    -0.06
    dration
    -0.06
    çī¹çļĦ
    -0.06
     ÎŃγι
    -0.06
     Gül
    -0.06
    wehr
    -0.06
     Ú©Ø´
    -0.06
    POSITIVE LOGITS
    äºİ人
    0.07
    çĶ¸
    0.07
    æĽ²
    0.07
    ĥ½
    0.07
    ÙĪÙĨÙĬØ©
    0.07
     ifndef
    0.07
    ëªħíķľ
    0.06
    vecs
    0.06
    ,proto
    0.06
    è·
    0.06
    Activations Density 0.002%

    No Known Activations