© 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. 22062
    Prev
    Next
    INDEX
    Explanations

    bifurcation

    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
    RefCount
    -0.08
    çĴŀ
    -0.07
     fermented
    -0.07
     Shack
    -0.07
    æĹ¥åĨħ
    -0.07
    _DIRS
    -0.07
     strides
    -0.07
    ÙħÙĨÙĬ
    -0.06
     Homemade
    -0.06
    ayer
    -0.06
    POSITIVE LOGITS
    æ¶Ī失
    0.08
     bif
    0.08
    çļĦæĶ¹åıĺ
    0.08
     breakpoint
    0.07
    çļĦé±¼
    0.07
    ело
    0.07
     saddle
    0.07
     disappearing
    0.07
    irsch
    0.07
     disappearance
    0.07
    Activations Density 0.014%

    No Known Activations