© 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. 11485
    Prev
    Next
    INDEX
    Explanations

    library includes and definitions

    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
    äºĶèĬ±
    -0.08
    麽
    -0.07
    walt
    -0.07
    ye
    -0.07
    letes
    -0.06
    åħĪå¾Ĺ
    -0.06
    æĺ¯æ°´
    -0.06
    æª
    -0.06
    åģĩ
    -0.06
    igny
    -0.06
    POSITIVE LOGITS
    }$/
    0.07
    zug
    0.07
    éĢĤéĩıçļĦ
    0.07
    å¹²åĺĽ
    0.07
    (',')
    0.07
    icales
    0.07
    çİ°è¡ĮçļĦ
    0.07
     âĵĴ
    0.07
    enez
    0.07
    .Serializable
    0.07
    Activations Density 0.003%

    No Known Activations