© 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. 3567
    Prev
    Next
    INDEX
    Explanations

    code and documentation

    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
    andalone
    -0.26
    Hôtel
    -0.21
    }-${
    -0.20
    .CompareTo
    -0.20
     offenses
    -0.19
    "is
    -0.19
     cerco
    -0.19
    .repeat
    -0.19
    'RE
    -0.19
    踯
    -0.19
    POSITIVE LOGITS
    grily
    0.23
     lineback
    0.22
    ook
    0.21
    ig
    0.20
    ony
    0.18
    routeProvider
    0.18
    -AA
    0.18
    çĿĢ
    0.18
    Truthy
    0.18
     Cav
    0.18
    Activations Density 0.028%

    No Known Activations