© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 56886
    Prev
    Next
    INDEX
    Explanations

    testing `:with` block

    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
    cy
    -0.07
    esson
    -0.07
    ILA
    -0.07
    çĽ¸å¯¹åºĶçļĦ
    -0.07
    æīĢ说çļĦ
    -0.07
    ÅĤaw
    -0.06
     cyber
    -0.06
    _DR
    -0.06
    antino
    -0.06
     Lah
    -0.06
    POSITIVE LOGITS
    ç«Ļç«Ļ
    0.08
    å¿ħèĥľ
    0.07
    umas
    0.07
     chamb
    0.07
    ãĥįãĥ«
    0.07
     blazing
    0.07
     Forces
    0.07
     Annonce
    0.07
    -than
    0.06
     onstage
    0.06
    Activations Density 0.136%

    No Known Activations