© 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. 2537
    Prev
    Next
    INDEX
    Explanations

    say 1

    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
     &
    -0.24
     ActionTypes
    -0.23
     actionTypes
    -0.21
    ::
    -0.20
    èµĦ产éĩįç»Ħ
    -0.20
    æĻĹ
    -0.20
     (
    -0.20
     Serialized
    -0.19
    :
    -0.19
     Rehab
    -0.19
    POSITIVE LOGITS
    ðŁĵIJ
    0.23
    ?option
    0.23
     Ksi
    0.23
    ĺ认
    0.23
    âļĹ
    0.22
    _HERE
    0.22
    ?v
    0.21
    %C
    0.21
    gua
    0.21
     ×Ķ×ķ×ĵ
    0.21
    Activations Density 0.014%

    No Known Activations