© 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. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 3399
    Prev
    Next
    INDEX
    Explanations

    have

    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
     disadv
    -0.22
    @dynamic
    -0.22
    oftware
    -0.21
    \application
    -0.21
    buat
    -0.21
    iffany
    -0.20
    .setDefault
    -0.20
    ekt
    -0.20
    nç
    -0.20
    .lastname
    -0.20
    POSITIVE LOGITS
    resizing
    0.20
    .Runtime
    0.19
    ={`${
    0.18
    æĹłä¸į
    0.18
    (DbContext
    0.18
    .getChildAt
    0.18
     pur
    0.18
    æĿ¾
    0.17
    .Has
    0.17
    obuf
    0.17
    Activations Density 0.003%

    No Known Activations