© 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. 38931
    Prev
    Next
    INDEX
    Explanations

    dot followed by net or blot

    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
    estelle
    -0.09
    ذج
    -0.08
    istrator
    -0.08
    skem
    -0.07
    erdale
    -0.07
    asca
    -0.07
    æłijä¸Ģ
    -0.07
    zÅij
    -0.07
    isted
    -0.07
    erland
    -0.07
    POSITIVE LOGITS
    ween
    0.08
    iog
    0.08
    wise
    0.07
    ìħĪ
    0.07
    adura
    0.07
    nev
    0.07
    ars
    0.07
    ody
    0.07
    ings
    0.07
    pling
    0.07
    Activations Density 0.005%

    No Known Activations