© 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. 51641
    Prev
    Next
    INDEX
    Explanations

    optimal control problem selection

    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
     bia
    -0.07
    èİ«åIJį
    -0.07
     Watt
    -0.07
    одо
    -0.07
    åĶ®ç¥¨
    -0.06
    çĶ©
    -0.06
     factura
    -0.06
    enca
    -0.06
    æĻ´å¤©
    -0.06
     scol
    -0.06
    POSITIVE LOGITS
    ikov
    0.08
     earliest
    0.08
    early
    0.07
     Fol
    0.07
     instantaneous
    0.07
    gol
    0.07
    éļ¨æĻĤ
    0.07
     Berm
    0.07
    æľĢä¼ĺ
    0.07
    prud
    0.07
    Activations Density 0.004%

    No Known Activations