© 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. 47255
    Prev
    Next
    INDEX
    Explanations

    numbers and currency

    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
    P
    -0.07
    C
    -0.07
    (
    -0.07
    é£
    -0.06
    '
    -0.06
    V
    -0.06
    身
    -0.06
    èµıå¿ĥæĤ¦
    -0.06
    (m
    -0.06
    ä½ķçŃī
    -0.06
    POSITIVE LOGITS
    ammo
    0.09
    STALL
    0.09
    stock
    0.08
    ikkan
    0.08
    NCY
    0.08
    infos
    0.08
     Stock
    0.08
    viso
    0.08
    -stock
    0.08
    onav
    0.08
    Activations Density 0.014%

    No Known Activations