© 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. 2126
    Prev
    Next
    INDEX
    Explanations

    helpful

    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
    >{!!
    -0.23
    	fields
    -0.20
     Esp
    -0.20
    stackpath
    -0.20
    ächt
    -0.19
    ë´ħ
    -0.19
    upos
    -0.19
     Marin
    -0.19
    Toast
    -0.19
     htmlentities
    -0.18
    POSITIVE LOGITS
    æľīæīĢ帮åĬ©
    0.26
     IonicModule
    0.22
    åĶ¤
    0.22
     helpful
    0.22
    :disable
    0.21
    oks
    0.21
    help
    0.21
    å¤Ł
    0.21
     Useful
    0.20
    帮åĬ©
    0.20
    Activations Density 0.257%

    No Known Activations