© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 2466
    Prev
    Next
    INDEX
    Explanations

    technical jargon

    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
    'email
    -0.23
    :numel
    -0.23
    -Cs
    -0.22
     Decompiled
    -0.22
    pone
    -0.21
    'options
    -0.21
     windowHeight
    -0.20
    @student
    -0.20
    olib
    -0.20
    .lu
    -0.20
    POSITIVE LOGITS
     airstrikes
    0.21
    /renderer
    0.21
    åħ¬å¹³
    0.21
    åħ³éĶ®åŃĹ
    0.20
    .dd
    0.20
    ä½ľåĿĬ
    0.19
    ///<
    0.19
    åħ³éĶ®è¯į
    0.19
    å§Ķç»Ħç»ĩéĥ¨
    0.18
    United
    0.18
    Activations Density 0.193%

    No Known Activations