© 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. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1574
    Prev
    Next
    INDEX
    Explanations

    is

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/qwen2.5-7B-it-layer-20-saes/pile/matryoshka/k-100
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     UIAlert
    -0.24
    å®ĥçļĦ
    -0.23
     its
    -0.23
    å®ĥæĺ¯
    -0.22
    å®ĥ
    -0.22
    ä½Ĩå®ĥ
    -0.21
    _WARNINGS
    -0.20
     it
    -0.20
     Its
    -0.20
    aris
    -0.19
    POSITIVE LOGITS
     incumbent
    0.24
     raining
    0.24
     toDate
    0.23
     customary
    0.23
    enegro
    0.22
     imperative
    0.21
     wise
    0.21
    ABCDEFGHIJKLMNOP
    0.21
     clear
    0.20
    ertime
    0.20
    Activations Density 1.075%

    No Known Activations