© 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. 43024
    Prev
    Next
    INDEX
    Explanations

    browser extensions

    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
    æķĻèĤ²ç½ij
    -0.08
    acre
    -0.07
    reso
    -0.07
    åĴĮ讯
    -0.07
    .DeepEqual
    -0.07
    éŀŃçĤ®
    -0.07
    çĨ¬å¤ľ
    -0.07
    eltu
    -0.07
     аваÑĢ
    -0.07
    ạng
    -0.06
    POSITIVE LOGITS
    åıĹå½±åĵį
    0.09
     enhancement
    0.08
    åıĹåĪ°å½±åĵį
    0.08
     Enhancement
    0.08
    ä¸ŃåĬłåħ¥
    0.08
    Decorator
    0.07
    enh
    0.07
     modification
    0.07
    ç»ķè¡Į
    0.07
    Modifier
    0.07
    Activations Density 0.380%

    No Known Activations