© 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. 1488
    Prev
    Next
    INDEX
    Explanations

    scaling mass redshift frequency

    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
     heck
    -0.08
    pled
    -0.07
    liner
    -0.07
     Kuh
    -0.07
    åijµ
    -0.07
    gemeinde
    -0.07
    poster
    -0.07
    好äºİ
    -0.07
    ÙĪارÙĩ
    -0.07
    æ¬ł
    -0.07
    POSITIVE LOGITS
    agos
    0.08
    æıIJä¾ĽåıĤèĢĥ
    0.08
    大åı¯
    0.07
    åıĤèĢĥ
    0.07
    RIX
    0.07
    embr
    0.07
    纯粹
    0.07
     scaling
    0.07
    eed
    0.07
    anga
    0.07
    Activations Density 0.004%

    No Known Activations