© 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. 13999
    Prev
    Next
    INDEX
    Explanations

    statement termination

    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
    ¹
    -0.08
     Poli
    -0.08
    çĿ£å¯Ł
    -0.08
    odaw
    -0.07
    -metadata
    -0.07
    çļĦè§Ĥå¯Ł
    -0.07
    едÑĥ
    -0.07
    suma
    -0.07
    един
    -0.07
    atos
    -0.07
    POSITIVE LOGITS
    ñas
    0.07
    èĥ¶
    0.07
    éĢĨ
    0.07
    annel
    0.06
    cke
    0.06
    笼
    0.06
    è£ı
    0.06
    kezés
    0.06
    \\/
    0.06
    ноÑģ
    0.06
    Activations Density 0.039%

    No Known Activations