© 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. 43060
    Prev
    Next
    INDEX
    Explanations

    `

    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
    enville
    -0.07
    ä¸ĩ家
    -0.06
     Verde
    -0.06
    ogy
    -0.06
    OnError
    -0.06
    lem
    -0.06
     Eck
    -0.06
    æľĿéĺ³åĮº
    -0.06
    æī«æııäºĮç»´çłģ
    -0.06
     fil
    -0.06
    POSITIVE LOGITS
    该åĨħ容
    0.08
    ɵ
    0.07
    ÑģÑĤно
    0.07
    å¡ĺ
    0.07
    æIJŃ
    0.07
    æħĭ
    0.07
     Laz
    0.07
    EFR
    0.07
     ãģĬçŁ¥ãĤīãģĽ
    0.07
    åĴĮæĢĿèĢĥ
    0.07
    Activations Density 0.243%

    No Known Activations