© 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. 2835
    Prev
    Next
    INDEX
    Explanations

    classification

    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
     shallow
    -0.23
     cellForRowAt
    -0.22
    sh
    -0.21
    s
    -0.20
    èģĶæĥ³
    -0.20
    æ»¨æ±Ł
    -0.19
     fontStyle
    -0.19
     facult
    -0.19
    oriously
    -0.19
    æľ«
    -0.18
    POSITIVE LOGITS
    ]={↵
    0.28
    :animated
    0.28
    }elseif
    0.27
    âĮĤ
    0.26
    :numel
    0.25
    :".$
    0.23
    ðŁıł
    0.23
    âļĹ
    0.23
     Bones
    0.22
    .Concurrent
    0.22
    Activations Density 0.001%

    No Known Activations