© 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. 2345
    Prev
    Next
    INDEX
    Explanations

    will

    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
     (!((
    -0.26
    (EFFECT
    -0.22
    REFERRED
    -0.20
    æľªæĿ¥çļĦ
    -0.20
     future
    -0.20
    "urls
    -0.19
    bindung
    -0.19
    %"><
    -0.19
     suce
    -0.19
    future
    -0.18
    POSITIVE LOGITS
     shortly
    0.26
     soon
    0.22
    äºīåıĸ
    0.21
    [strlen
    0.21
     später
    0.20
    åı¦è¡Į
    0.20
    æķ´çIJĨ
    0.19
     Soon
    0.19
    ippines
    0.19
    trys
    0.18
    Activations Density 0.317%

    No Known Activations