© 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. 416
    Prev
    Next
    INDEX
    Explanations

    Brett

    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
    âĸ·
    -0.42
    __;
    -0.40
    ï¹¢
    -0.37
     èĭ¥è¦ģ
    -0.37
    NCY
    -0.36
     *))
    -0.36
    âĨĹ
    -0.35
    ãĢĥ
    -0.35
     ×Ķ×ķ×ĵ
    -0.35
    uckland
    -0.35
    POSITIVE LOGITS
    1
    0.35
    3
    0.33
    0
    0.33
    2
    0.33
     masturbating
    0.32
    4
    0.30
    5
    0.29
    9
    0.29
    6
    0.28
    8
    0.28
    Activations Density 12.104%

    No Known Activations