© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 908
    Prev
    Next
    INDEX
    Explanations

    math calculations

    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
     Redistributions
    -0.22
    .EventQueue
    -0.22
    个çĻ¾åĪĨ
    -0.22
    åı¯æĥ³èĢĮ
    -0.22
    .fromRGBO
    -0.21
     UsersController
    -0.21
    izabeth
    -0.20
    Ĥæķ°
    -0.20
     lawy
    -0.20
    bih
    -0.20
    POSITIVE LOGITS
    ths
    0.24
    )throws
    0.22
    toPromise
    0.21
    ipzig
    0.20
    <footer
    0.19
    /lists
    0.19
    ////↵
    0.19
    izarre
    0.19
    Uvs
    0.19
    åĨ²
    0.19
    Activations Density 0.359%

    No Known Activations