© 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. 64366
    Prev
    Next
    INDEX
    Explanations

    reversed, reorder

    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
    åŀ£
    -0.07
    trib
    -0.07
    elay
    -0.06
     nom
    -0.06
    æ¸ħéĻ¤
    -0.06
    åĩºäºº
    -0.06
    WA
    -0.06
     too
    -0.06
    uration
    -0.06
    ä¸İ伦
    -0.06
    POSITIVE LOGITS
    é¢łåĢĴ
    0.09
     reversal
    0.08
     berw
    0.08
    бан
    0.08
    umen
    0.08
     reversed
    0.08
     reorder
    0.08
    azes
    0.08
    odom
    0.08
    éĢĨåIJij
    0.08
    Activations Density 0.001%

    No Known Activations