© 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. 386
    Prev
    Next
    INDEX
    Explanations

    code or programming

    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
    ľ
    -0.24
    è´µ
    -0.22
    brig
    -0.19
    иÑĢов
    -0.19
    é¾Ī
    -0.19
    ContextHolder
    -0.18
    uml
    -0.18
     japan
    -0.18
    VIS
    -0.18
    âĬĸ
    -0.18
    POSITIVE LOGITS
    zbek
    0.23
    ald
    0.22
    gregar
    0.21
     masturbating
    0.21
    åķŃ
    0.20
    ÑİÑīего
    0.20
    :"#
    0.20
    icol
    0.20
    kü
    0.20
    indsay
    0.20
    Activations Density 0.001%

    No Known Activations