© 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. 3804
    Prev
    Next
    INDEX
    Explanations

    negation

    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
     ÑģенÑĤÑı
    -0.21
    æ¿Ĵ
    -0.20
     ÑıнваÑĢ
    -0.20
     aDecoder
    -0.19
     окÑĤÑı
    -0.19
    pic
    -0.18
    åıĪ好åıĪå¿«
    -0.18
     darkest
    -0.18
     activeClassName
    -0.18
     авгÑĥÑģÑĤ
    -0.18
    POSITIVE LOGITS
    容
    0.24
     GiỼi
    0.23
    âĹĤ
    0.23
    ðŁķij
    0.23
    /XML
    0.22
    hế
    0.22
    -CN
    0.22
    NullOr
    0.21
    <quote
    0.21
    "id
    0.21
    Activations Density 0.474%

    No Known Activations