© 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. 39048
    Prev
    Next
    INDEX
    Explanations

    ãĢī / math/science notation

    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
    en
    -0.07
    atic
    -0.07
    ali
    -0.06
    élé
    -0.06
    tih
    -0.05
    -0.05
    Âł
    -0.05
    er
    -0.05
    pane
    -0.05
    ën
    -0.05
    POSITIVE LOGITS
    vrier
    0.10
    ihak
    0.09
    ponge
    0.09
    oland
    0.08
    ulich
    0.08
    ystems
    0.08
    itespace
    0.08
    vegli
    0.08
    achel
    0.08
    resenter
    0.08
    Activations Density 0.047%

    No Known Activations