© 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. 24342
    Prev
    Next
    INDEX
    Explanations

    logarithm and transform

    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
    åħ´
    -0.08
    _unused
    -0.08
    _DF
    -0.08
    åı¯å¢ŀåĬł
    -0.07
    ä¸įæī¿æĭħä»»ä½ķ
    -0.07
    çİĭåºľ
    -0.07
    egel
    -0.07
    cias
    -0.07
     discharged
    -0.07
    ãĤ¹ãĥĶ
    -0.07
    POSITIVE LOGITS
    arith
    0.09
    -log
    0.09
     log
    0.08
     logarith
    0.08
    =log
    0.08
     transform
    0.08
    -transform
    0.07
    ified
    0.07
    inary
    0.07
    log
    0.07
    Activations Density 0.008%

    No Known Activations