© 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. 20881
    Prev
    Next
    INDEX
    Explanations

    cost per unit

    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
    agn
    -0.07
    èĮ«èĮ«
    -0.07
    å°¼æĸ¯
    -0.07
    iris
    -0.07
    enko
    -0.07
    ñez
    -0.07
    nij
    -0.07
     ÙĥÙĦÙĩ
    -0.06
    acz
    -0.06
    亿人
    -0.06
    POSITIVE LOGITS
     اÙĦÙĪاØŃد
    0.10
     اÙĦÙĪا
    0.09
    çıĬ
    0.08
    Ùĩاب
    0.08
    æĪIJæľ¬
    0.08
     cost
    0.08
    kost
    0.08
    .cost
    0.07
     ENC
    0.07
    /module
    0.07
    Activations Density 0.022%

    No Known Activations