© 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. 376
    Prev
    Next
    INDEX
    Explanations

    X

    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
    zÅĤ
    -0.37
     tü
    -0.36
     misunder
    -0.36
    iets
    -0.35
     öl
    -0.35
     Erotic
    -0.34
    achelor
    -0.33
    .omg
    -0.33
    ibrator
    -0.33
    âļĹ
    -0.33
    POSITIVE LOGITS
    TERNAL
    0.30
     “
    0.26
    avier
    0.26
    0.24
    ed
    0.23
    ation
    0.23
    es
    0.23
     (
    0.23
     un
    0.23
    -
    0.22
    Activations Density 3.867%

    No Known Activations