© 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. 3588
    Prev
    Next
    INDEX
    Explanations

    digits

    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
    Versions
    -0.25
    ceptar
    -0.24
    ercial
    -0.20
    à¸īà¸ļ
    -0.19
    _Query
    -0.19
    innitus
    -0.19
    _vlan
    -0.19
    istrator
    -0.19
    ейÑĩаÑģ
    -0.19
     Poly
    -0.18
    POSITIVE LOGITS
     Seamless
    0.23
     fkk
    0.21
    olute
    0.21
    MOTE
    0.20
    SEQUENTIAL
    0.20
    +:
    0.19
    /umd
    0.19
    ä¸Ĭ游
    0.19
    -sm
    0.19
    клÑİÑĩа
    0.19
    Activations Density 0.214%

    No Known Activations