© 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. 1659
    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
     decltype
    -0.19
     banged
    -0.18
    ublic
    -0.18
    ÑĥниÑĨип
    -0.18
    _DEL
    -0.18
    _RB
    -0.18
    _firstname
    -0.18
    ãģķãģĦ
    -0.18
     anmeld
    -0.18
    alian
    -0.18
    POSITIVE LOGITS
    }());↵
    0.28
     :";↵
    0.26
    :checked
    0.23
    apt
    0.23
     ******************************************************************************↵
    0.22
    strar
    0.22
     [~,
    0.20
    ocations
    0.20
    .clipsToBounds
    0.20
    endir
    0.19
    Activations Density 0.002%

    No Known Activations