© 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. 55599
    Prev
    Next
    INDEX
    Explanations

    square root

    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
    çĶ©
    -0.09
    entino
    -0.09
     NotImplemented
    -0.08
    ä¸ĸåŃIJ
    -0.08
    工贸
    -0.08
    utenberg
    -0.08
    ILED
    -0.08
    SIDE
    -0.08
     privilegi
    -0.08
    зино
    -0.08
    POSITIVE LOGITS
    (s
    0.08
    arro
    0.06
    åIJĮé¾Ħ
    0.06
    åĽ¢åĽ¢
    0.06
     square
    0.06
    oot
    0.06
     everywhere
    0.06
    åºķçļĦ
    0.06
    isible
    0.06
    appa
    0.06
    Activations Density 0.004%

    No Known Activations