© 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. 12858
    Prev
    Next
    INDEX
    Explanations

    complex algebraic structures

    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
    iggio
    -0.09
    /ajax
    -0.08
     stair
    -0.07
     fr
    -0.07
    å¾Ļ
    -0.07
    baseline
    -0.07
    ikt
    -0.07
     baseline
    -0.07
    åľ¨èģĮ
    -0.07
    olini
    -0.07
    POSITIVE LOGITS
    æī©åħħ
    0.09
    æī©å±ķ
    0.09
    _expand
    0.08
     expanded
    0.08
    embed
    0.08
    _resolve
    0.07
    åĪĨ解
    0.07
    å¢ĥ
    0.07
    ries
    0.07
    æī©
    0.07
    Activations Density 0.007%

    No Known Activations