© 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. 3732
    Prev
    Next
    INDEX
    Explanations

    technical 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
    :animated
    -0.27
    reeNode
    -0.24
     REQUIRED
    -0.19
    -Requested
    -0.19
    erialize
    -0.19
    TabIndex
    -0.19
    puties
    -0.19
    dziaÅĤ
    -0.19
    ulp
    -0.18
    liable
    -0.18
    POSITIVE LOGITS
    .dtd
    0.21
     +=↵
    0.20
     {č↵č↵č↵
    0.20
    IDEO
    0.20
    EDITOR
    0.19
     LoginComponent
    0.19
    коло
    0.18
    SSH
    0.18
    CRC
    0.18
    _Interface
    0.18
    Activations Density 0.001%

    No Known Activations