© 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. 23467
    Prev
    Next
    INDEX
    Explanations

    names followed by "is" or "has"

    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
    ool
    -0.08
    ä»ĸå°±ä¼ļ
    -0.08
    eiro
    -0.08
    å°±å¾Ģ
    -0.08
    ezza
    -0.07
    enste
    -0.07
    åĮ¹
    -0.07
     gesta
    -0.07
    reation
    -0.07
    ools
    -0.07
    POSITIVE LOGITS
     therefore
    0.09
     ëĺIJíķľ
    0.08
    ä¹ŁåĽłæѤ
    0.08
     also
    0.08
     ÑĤакже
    0.07
     également
    0.07
    cc
    0.07
     inoltre
    0.07
    olog
    0.07
     thus
    0.06
    Activations Density 0.006%

    No Known Activations