© 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. 3585
    Prev
    Next
    INDEX
    Explanations

    named entities

    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
    grily
    -0.23
    Verdana
    -0.21
     COPYRIGHT
    -0.21
    èĦ±é¢ĸ
    -0.21
    |required
    -0.20
     grues
    -0.20
     inflamm
    -0.20
     Bedrooms
    -0.20
     Bald
    -0.20
    loads
    -0.19
    POSITIVE LOGITS
    |--------------------------------------------------------------------------↵
    0.21
     spyOn
    0.20
    .jwt
    0.20
    еÑĤÑĮ
    0.20
    ubbo
    0.19
    brid
    0.19
    uur
    0.19
    _org
    0.19
     cross
    0.19
     tent
    0.18
    Activations Density 0.001%

    No Known Activations