© 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. 10997
    Prev
    Next
    INDEX
    Explanations

    invention, method, service, thereof

    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
    êm
    -0.07
    è¨Ģ
    -0.06
    çĶ©
    -0.06
     phantom
    -0.06
    å¦Ħæĥ³
    -0.06
    Whilst
    -0.06
    !!!!
    -0.06
    ÙĤÙĬات
    -0.06
    åħĭ森
    -0.06
    új
    -0.06
    POSITIVE LOGITS
    sov
    0.08
    indr
    0.08
    arella
    0.07
    ë·°
    0.07
    жнÑı
    0.07
    pek
    0.07
    onte
    0.07
    eni
    0.07
    $('
    0.07
    pci
    0.07
    Activations Density 0.401%

    No Known Activations