© 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. 25503
    Prev
    Next
    INDEX
    Explanations

    forms of "to be" followed by descriptions

    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
    ervers
    -0.08
    以ä¸Ĭå°±æĺ¯åħ³äºİ
    -0.07
    azan
    -0.07
    chand
    -0.07
    fri
    -0.07
    /*@
    -0.07
    以ä¸Ĭå°±æĺ¯å°ıç¼ĸ
    -0.07
    furt
    -0.07
    ousel
    -0.07
    ãģĭãģ§
    -0.07
    POSITIVE LOGITS
    à¸Ķัà¸ĩà¸Ļีà¹ī
    0.08
    оÑĢи
    0.07
     basically
    0.07
     anything
    0.07
    èİ«è¿ĩäºİ
    0.07
    :
    0.07
    tn
    0.07
    unge
    0.06
    å¦Ĥä¸ĭ
    0.06
     firstly
    0.06
    Activations Density 0.760%

    No Known Activations