© 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. 18859
    Prev
    Next
    INDEX
    Explanations

    siglas with letters like 'c', 'r', 't', 'd'

    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
    nya
    -0.10
    ele
    -0.10
    eam
    -0.08
    ezi
    -0.08
    erb
    -0.08
    ead
    -0.07
    ez
    -0.07
    ãĥ³ãĤ°
    -0.07
    eur
    -0.07
    each
    -0.07
    POSITIVE LOGITS
    rosse
    0.09
    .parseFloat
    0.09
    /St
    0.09
    -Sah
    0.09
    adays
    0.09
    ennen
    0.08
    itage
    0.08
    /Set
    0.08
    -Fi
    0.08
    semble
    0.08
    Activations Density 0.321%

    No Known Activations