© 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. 11475
    Prev
    Next
    INDEX
    Explanations

    CASE FILE, testcase, information retrieval

    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
    æŁ¥çľĭåħ¨éĥ¨
    -0.07
    使çĶ¨æĸ¹ä¾¿
    -0.07
    iaan
    -0.07
    /package
    -0.07
    ernals
    -0.07
    quo
    -0.07
    转载æĪĸ
    -0.07
    θη
    -0.07
    åijĬ
    -0.07
    èħ¾è®¯å¾®åįļ
    -0.07
    POSITIVE LOGITS
     reasoning
    0.09
    æĥħæĦŁ
    0.08
     AI
    0.08
    æݨçIJĨ
    0.08
    heur
    0.07
     score
    0.07
     dataset
    0.07
    çĶĦ
    0.07
     advers
    0.07
     diá»ħn
    0.07
    Activations Density 0.228%

    No Known Activations