© 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. 49629
    Prev
    Next
    INDEX
    Explanations

    recursion

    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
     Mash
    -0.07
    gur
    -0.07
    uris
    -0.07
    enin
    -0.06
    upan
    -0.06
    æĻ¯
    -0.06
    ins
    -0.06
    _transient
    -0.06
    æģĭæĥħ
    -0.06
    upas
    -0.06
    POSITIVE LOGITS
    éĢĴå½Ĵ
    0.11
     recursively
    0.09
     recursion
    0.09
     Recursive
    0.09
    Recursive
    0.09
     recursive
    0.09
     depth
    0.08
    éĢĴ
    0.08
    Depth
    0.08
    depth
    0.08
    Activations Density 0.043%

    No Known Activations