© 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. 47412
    Prev
    Next
    INDEX
    Explanations

    equals or composition

    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
    veau
    -0.09
    èľĤ
    -0.07
    声声
    -0.07
    ä¸ĩåħ¬éĩĮ
    -0.07
    heit
    -0.07
    çļĦéĩįè¦ģåİŁåĽł
    -0.06
    vég
    -0.06
    移è¡Į
    -0.06
    LV
    -0.06
    _ix
    -0.06
    POSITIVE LOGITS
    oucher
    0.08
     Equals
    0.08
    Equals
    0.08
     equals
    0.08
    çŃīäºİ
    0.08
    pile
    0.08
    usen
    0.07
    rc
    0.07
    equals
    0.07
    à¸Ħ
    0.07
    Activations Density 0.005%

    No Known Activations