© 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. 18775
    Prev
    Next
    INDEX
    Explanations

    numbers and letters in sequences

    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
    leftright
    -0.08
    estand
    -0.07
    ltra
    -0.07
    ltr
    -0.07
    culus
    -0.07
     alber
    -0.07
    积çĶµ
    -0.07
    æݸ
    -0.06
    ovid
    -0.06
    aling
    -0.06
    POSITIVE LOGITS
    éĤ£å¤´
    0.07
     carn
    0.07
    dot
    0.06
    uchu
    0.06
    dit
    0.06
    b
    0.06
    eron
    0.06
    .ng
    0.06
    ÑģÑĤина
    0.06
    令
    0.06
    Activations Density 0.011%

    No Known Activations