© 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. 3709
    Prev
    Next
    INDEX
    Explanations

    half

    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
    ¾
    -0.20
    ?family
    -0.20
    èįĥ
    -0.19
     Bert
    -0.19
    plusplus
    -0.19
    rijk
    -0.18
    perience
    -0.18
    åĨĨ
    -0.18
    éĤ»
    -0.17
    onestly
    -0.17
    POSITIVE LOGITS
    ä¸īåĪĨä¹ĭä¸Ģ
    0.36
    ä¸ĢåįĬ
    0.32
    addContainerGap
    0.28
    âļĹ
    0.26
    ä¸Ńéĥ¨
    0.25
    åįĬ
    0.25
     halfway
    0.25
    ä¸ŃéĹ´
    0.25
     полов
    0.25
     half
    0.24
    Activations Density 0.265%

    No Known Activations