© 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. 4037
    Prev
    Next
    INDEX
    Explanations

    extracting variable assignments

    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
    å°½äºĨ
    -0.08
    équ
    -0.07
    issippi
    -0.07
    产çļĦ
    -0.07
    mtx
    -0.07
    产
    -0.07
    çĥŃåĬĽ
    -0.07
    ailles
    -0.07
    è¥
    -0.07
    å±ŀ
    -0.07
    POSITIVE LOGITS
    extract
    0.10
     indicated
    0.09
     extracted
    0.09
     Aster
    0.08
    éļIJèĹıåľ¨
    0.08
     Extract
    0.08
     extract
    0.08
    èĹıåľ¨
    0.08
     encoded
    0.08
    Extract
    0.08
    Activations Density 0.184%

    No Known Activations