© 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. 57007
    Prev
    Next
    INDEX
    Explanations

    logarithm, logarithmic, logging

    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
    à¸Ĺà¹Į
    -0.10
    ergestellt
    -0.09
    OrElse
    -0.09
     ÐĶополни
    -0.09
    orca
    -0.08
    Åijl
    -0.08
    iful
    -0.08
    ç½ĹéĤ£
    -0.08
    orama
    -0.07
    gaard
    -0.07
    POSITIVE LOGITS
    arith
    0.12
    ic
    0.10
    onso
    0.08
    ı
    0.08
    os
    0.08
    ically
    0.07
    ounge
    0.07
    mic
    0.07
    oidal
    0.07
    gev
    0.07
    Activations Density 0.002%

    No Known Activations