© 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. 10398
    Prev
    Next
    INDEX
    Explanations

    list columns and except

    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
    AMI
    -0.07
    xBA
    -0.07
    obl
    -0.06
    åįģäºĮ
    -0.06
     tun
    -0.06
    ugno
    -0.06
     Haw
    -0.06
    >H
    -0.06
    äºĶ
    -0.06
    éļIJ
    -0.06
    POSITIVE LOGITS
     ấp
    0.09
    ä¸Ńä¹ĭ
    0.09
    lander
    0.08
    atch
    0.07
    _pressed
    0.07
    imited
    0.07
     پاک
    0.07
    åŃĹçĶ»
    0.07
    ikai
    0.07
     Rect
    0.07
    Activations Density 0.005%

    No Known Activations