© 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. 27438
    Prev
    Next
    INDEX
    Explanations

    mathematical terms containing specific properties

    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
    chetto
    -0.09
    afil
    -0.08
    ADI
    -0.08
    .getSeconds
    -0.07
    oppable
    -0.07
    .Convert
    -0.07
    åıijçİ°
    -0.07
    zak
    -0.07
    alda
    -0.07
     Busty
    -0.07
    POSITIVE LOGITS
     specified
    0.12
    æĮĩå®ļ
    0.10
    specified
    0.09
    æĮĩå®ļçļĦ
    0.09
     specifies
    0.09
     specify
    0.09
     specifying
    0.09
     specifications
    0.09
     specification
    0.08
     Specify
    0.08
    Activations Density 0.009%

    No Known Activations