© 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. 12825
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and variables

    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
    åIJı
    -0.08
    ä¿IJ
    -0.07
    ervas
    -0.07
     Renzi
    -0.07
    pid
    -0.07
    _SAFE
    -0.07
    et
    -0.07
    ее
    -0.07
    æ´ģ
    -0.07
    beam
    -0.06
    POSITIVE LOGITS
    ceg
    0.09
     respectively
    0.09
    entes
    0.07
    _submission
    0.07
     Lega
    0.07
    bral
    0.07
    åĽłä¸ºå®ĥ们
    0.07
    illage
    0.07
     respective
    0.06
    åĪĨåĪ«ä¸º
    0.06
    Activations Density 0.015%

    No Known Activations