© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1905
    Prev
    Next
    INDEX
    Explanations

    code or structure

    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
    aeda
    -0.25
    /Instruction
    -0.24
    âļĹ
    -0.22
    ,DB
    -0.22
     íĨµíķĺìŬ
    -0.22
     søger
    -0.21
    Cadastro
    -0.20
     Venezuel
    -0.20
    alsex
    -0.20
     (::
    -0.20
    POSITIVE LOGITS
    .realpath
    0.23
    .RequestParam
    0.22
    .LEADING
    0.20
    年人
    0.20
    (nextProps
    0.19
     Rudy
    0.19
    ToLeft
    0.19
    ç¾İåªĴ
    0.19
    å©ī
    0.19
    @student
    0.19
    Activations Density 0.080%

    No Known Activations