© 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. 21112
    Prev
    Next
    INDEX
    Explanations

    logarithm and related functions

    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
    nell
    -0.08
    enang
    -0.07
    æĿİè½»
    -0.07
    nalité
    -0.07
    UDO
    -0.07
    aat
    -0.07
    nel
    -0.07
    cente
    -0.07
    íĹĮ
    -0.07
    ognito
    -0.07
    POSITIVE LOGITS
    漪
    0.08
    arith
    0.08
    ä¸ĩçī©
    0.07
    ärt
    0.07
    AuthProvider
    0.07
    Cum
    0.07
    erner
    0.07
    å®Ĺ
    0.07
    azard
    0.06
    afen
    0.06
    Activations Density 0.005%

    No Known Activations