© 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. 3769
    Prev
    Next
    INDEX
    Explanations

    technical research

    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
    .centerX
    -0.23
    UILayout
    -0.22
    paralleled
    -0.21
    forgettable
    -0.21
    .removeListener
    -0.20
    Ã¼ÃŁ
    -0.20
    ?url
    -0.20
    NullOr
    -0.19
     w
    -0.18
    .Design
    -0.18
    POSITIVE LOGITS
    -scenes
    0.28
     FixedUpdate
    0.24
    nings
    0.24
     Decompiled
    0.23
    ]<<
    0.23
    ;line
    0.22
    'icon
    0.22
    è°Ĩ
    0.22
     ^=
    0.21
     spécialisé
    0.21
    Activations Density 0.014%

    No Known Activations