© 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. 3608
    Prev
    Next
    INDEX
    Explanations

    errors or code

    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
    \OptionsResolver
    -0.22
    Borders
    -0.20
    xfff
    -0.20
    gency
    -0.20
    meric
    -0.20
     Narc
    -0.20
    ustralian
    -0.20
     Flem
    -0.20
     Elev
    -0.19
    :'',
    -0.19
    POSITIVE LOGITS
    "errors
    0.22
    ä¼Ľ
    0.21
     aras
    0.21
    轫
    0.21
    gnore
    0.21
     =>$
    0.20
     inh
    0.20
    âݨ
    0.20
    (gcf
    0.20
    <fieldset
    0.20
    Activations Density 0.001%

    No Known Activations