© 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. 2312
    Prev
    Next
    INDEX
    Explanations

    gastric, constructor, minority, infinitive

    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
    ipay
    -0.08
     ([[
    -0.07
    ik
    -0.07
     (âĢŀ
    -0.07
     («
    -0.07
     ep
    -0.07
     kelu
    -0.07
    umbo
    -0.07
    ãĤ¤ãĤ¯
    -0.07
    pak
    -0.06
    POSITIVE LOGITS
    ugat
    0.07
    utati
    0.06
    aturi
    0.06
    YW
    0.06
     évent
    0.06
    ä¸İä¼Ĺ
    0.06
    å¹²èĦĨ
    0.06
    ä¸įèĩª
    0.06
    atable
    0.06
    _strlen
    0.06
    Activations Density 0.035%

    No Known Activations