© 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. 19589
    Prev
    Next
    INDEX
    Explanations

    programming constructs and 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
    ongen
    -0.08
     continuing
    -0.08
    ä¸ĢåĽŀäºĭ
    -0.07
    åĨħ容æľī
    -0.07
    å®ĥæľī
    -0.07
    iran
    -0.06
    ansk
    -0.06
     Simply
    -0.06
    åĪĻæľī
    -0.06
     lur
    -0.06
    POSITIVE LOGITS
    tourn
    0.08
    Ł
    0.07
     Walters
    0.07
    ieno
    0.07
    nico
    0.07
    terer
    0.07
     Muhamm
    0.07
    è¿Ļå°ıåŃIJ
    0.07
    atique
    0.07
    çł´çĥĤ
    0.07
    Activations Density 0.100%

    No Known Activations