© 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. 40762
    Prev
    Next
    INDEX
    Explanations

    math expressions with parentheses

    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
    etal
    -0.08
    haft
    -0.07
    asca
    -0.07
    جاÙĨ
    -0.06
    делÑĭ
    -0.06
    éĶ¦æ¶Ľ
    -0.06
    est
    -0.06
    chester
    -0.06
    prost
    -0.06
    失
    -0.06
    POSITIVE LOGITS
    aku
    0.08
     parentheses
    0.07
    anee
    0.07
    ÙĪÙħÙĩ
    0.07
    Paren
    0.07
     minus
    0.07
    mena
    0.07
    ((((
    0.07
    ohana
    0.07
    çĭłçĭłåľ°
    0.06
    Activations Density 0.009%

    No Known Activations