© 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. 15148
    Prev
    Next
    INDEX
    Explanations

    specifications, theory, delivery, leads, protocol

    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
    ÙĪتÙĬ
    -0.07
    èIJ¨æĸ¯
    -0.07
     convers
    -0.07
    ouz
    -0.06
    å¦Ĥå±±
    -0.06
    ectes
    -0.06
    åĴ¯åĴ¯
    -0.06
    aska
    -0.06
     convainc
    -0.06
    庸
    -0.06
    POSITIVE LOGITS
    pees
    0.07
    maal
    0.07
    ×Ļ×Ļ×Ŀ
    0.07
    çĦ¼
    0.07
    sts
    0.06
    以ä¸Ģç§į
    0.06
    liced
    0.06
    èĦ±
    0.06
    ásticas
    0.06
    led
    0.06
    Activations Density 0.662%

    No Known Activations