© 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. 15020
    Prev
    Next
    INDEX
    Explanations

    function completion

    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
     transient
    -0.06
    (inst
    -0.06
    åĬłéĢŁ
    -0.06
     hum
    -0.06
    ait
    -0.06
    ç²¾
    -0.06
    ç¦ģå¿Į
    -0.06
    ®
    -0.06
    enberg
    -0.06
     hoops
    -0.06
    POSITIVE LOGITS
    å®Ŀåīij
    0.09
    nga
    0.09
    bras
    0.08
    heits
    0.08
    svm
    0.08
     positive
    0.08
    illas
    0.08
    epas
    0.08
    positive
    0.08
    lse
    0.07
    Activations Density 0.010%

    No Known Activations