© 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. 28723
    Prev
    Next
    INDEX
    Explanations

    last id or start link

    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
    OMEM
    -0.08
    ivre
    -0.07
    /Runtime
    -0.07
    åĬłæĭī
    -0.07
    urry
    -0.07
     premature
    -0.07
     Basic
    -0.07
    prem
    -0.07
    åĴĮåŁºæľ¬
    -0.06
    æıIJæĹ©
    -0.06
    POSITIVE LOGITS
    çĬĢ
    0.07
    女士
    0.07
    oser
    0.07
    ä¸ĭä¸Ģ个
    0.07
    å·¥çŁ¿
    0.07
    ä¸ĭä¸Ģ
    0.07
     ngưỡng
    0.07
    æIJľç´¢
    0.07
    stricted
    0.07
    edList
    0.07
    Activations Density 0.040%

    No Known Activations