© 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. 1566
    Prev
    Next
    INDEX
    Explanations

    genetics, DNA

    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
    CCI
    -0.22
     borderTop
    -0.22
     borderBottom
    -0.20
    .Dto
    -0.20
    æŁ¥çľĭåħ¨æĸĩ
    -0.19
    ìĻ¼
    -0.19
    _Panel
    -0.19
     perc
    -0.19
    OCUMENT
    -0.19
     CharSequence
    -0.18
    POSITIVE LOGITS
    :host
    0.26
    ç»ĦåĽ¾
    0.25
    urnished
    0.23
    .WindowManager
    0.21
    代
    0.21
    :'.$
    0.21
    {!!
    0.21
    èħ¾
    0.20
     disrespectful
    0.20
    structuring
    0.20
    Activations Density 0.016%

    No Known Activations