© 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. 12103
    Prev
    Next
    INDEX
    Explanations

    adding '+' to numbers

    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
    zey
    -0.08
    _DECLS
    -0.08
    ayi
    -0.07
    ="__
    -0.07
    çĻ¾åħĥ
    -0.07
    åIJĦçıŃ
    -0.07
    umus
    -0.07
    avers
    -0.07
    lica
    -0.07
    .Are
    -0.07
    POSITIVE LOGITS
    åħ·å¤ĩ
    0.07
    lais
    0.07
    ilent
    0.07
    ords
    0.06
    ron
    0.06
    ±
    0.06
    è®©æĽ´å¤ļ
    0.06
    пÑĢе
    0.06
    åı¥å¼ı
    0.06
    sang
    0.06
    Activations Density 0.001%

    No Known Activations