© 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. 16964
    Prev
    Next
    INDEX
    Explanations

    intermediate values or states

    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
    utzer
    -0.08
    管好
    -0.07
    elly
    -0.07
    为é¦ĸçļĦ
    -0.07
    ardini
    -0.07
    ÑĪком
    -0.07
    .extensions
    -0.07
    大åĬ¿
    -0.07
    ombine
    -0.07
     rentrée
    -0.07
    POSITIVE LOGITS
     intermediate
    0.22
    Intermediate
    0.18
     Intermediate
    0.18
     intermedi
    0.17
     пÑĢомежÑĥ
    0.17
    ä¸ŃéĹ´
    0.17
     intermediary
    0.16
    ä¸ŃéĹ´ä½ĵ
    0.14
     Zwischen
    0.14
    ä¸Ńéĸĵ
    0.14
    Activations Density 0.051%

    No Known Activations