© 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. 3697
    Prev
    Next
    INDEX
    Explanations

    meet needs and requirements

    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
    ratulations
    -0.24
    %@",
    -0.22
    loquent
    -0.22
    meldung
    -0.21
     rencont
    -0.21
    upert
    -0.21
    erable
    -0.20
    olu
    -0.20
    ábado
    -0.20
    onsense
    -0.20
    POSITIVE LOGITS
     requirements
    0.38
     demands
    0.34
    çļĦè¦ģæ±Ĥ
    0.33
    requirements
    0.32
    éľĢæ±Ĥ
    0.31
     Requirements
    0.30
     needs
    0.29
    Requirements
    0.29
    è¦ģæ±Ĥ
    0.29
     ÑĤÑĢебованиÑı
    0.28
    Activations Density 0.278%

    No Known Activations