© 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. 46867
    Prev
    Next
    INDEX
    Explanations

    circular, loop, cyclic, circle, crossover

    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
    úp
    -0.09
    ä¹ĭè¾Ī
    -0.08
    CDATA
    -0.07
    Rocket
    -0.07
    সা
    -0.07
    _robot
    -0.07
    åIJĦ级åIJĦç±»
    -0.07
    zcze
    -0.07
     Rocket
    -0.07
    çģ«ç®Ń
    -0.07
    POSITIVE LOGITS
    循çݯ
    0.09
    çݯ形
    0.07
    çݯ
    0.07
     Circular
    0.07
     loop
    0.07
    ircular
    0.07
     circle
    0.07
     circular
    0.07
     uniform
    0.07
    loops
    0.07
    Activations Density 0.007%

    No Known Activations