© 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. 20677
    Prev
    Next
    INDEX
    Explanations

    numbers in equations

    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
     tre
    -0.07
    è´¯
    -0.07
    çĭ¬ç«ĭ
    -0.07
    iao
    -0.06
    Persist
    -0.06
    èĤĩ
    -0.06
    tre
    -0.06
    æĮģä¹ħ
    -0.06
    ä¸įåıĹ
    -0.06
    eldon
    -0.06
    POSITIVE LOGITS
    odz
    0.09
    quee
    0.08
     Ata
    0.08
    rafa
    0.08
    emd
    0.08
    æĺĬ天
    0.08
    edm
    0.08
    aton
    0.08
    опо
    0.08
    ีà¹Īà¸Ľ
    0.07
    Activations Density 0.019%

    No Known Activations