© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1059
    Prev
    Next
    INDEX
    Explanations

    S

    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
    regunta
    -0.20
     Tells
    -0.20
    FormsModule
    -0.20
    ndl
    -0.20
     Bearings
    -0.20
    åij£
    -0.20
    rello
    -0.20
    /lg
    -0.19
    Türkiye
    -0.19
     Interracial
    -0.19
    POSITIVE LOGITS
    عÙĪد
    0.20
    å®īå±ħ
    0.19
    女æĺŁ
    0.19
    (Dictionary
    0.19
     (;;
    0.19
    :animated
    0.19
    etri
    0.19
    .isLoggedIn
    0.18
    raisal
    0.18
     resulting
    0.18
    Activations Density 0.010%

    No Known Activations