© 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. 33090
    Prev
    Next
    INDEX
    Explanations

    programming syntax and mathematical equations

    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
    å¾Ĵæīĭ
    -0.07
     alt
    -0.07
    inator
    -0.07
    ovid
    -0.06
     Alt
    -0.06
    sworth
    -0.06
    Ĥ
    -0.06
     Perc
    -0.06
    æıĸ
    -0.06
     exped
    -0.06
    POSITIVE LOGITS
    richten
    0.08
    Fade
    0.08
    porn
    0.08
    grese
    0.08
    isses
    0.08
     Monitoring
    0.08
    -progress
    0.07
     dissip
    0.07
    endt
    0.07
     monitored
    0.07
    Activations Density 0.001%

    No Known Activations