© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 659
    Prev
    Next
    INDEX
    Explanations

    point

    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
    æĤĮ
    -0.25
    ENA
    -0.23
    twor
    -0.23
    icorn
    -0.21
    enz
    -0.21
    /bind
    -0.20
    enha
    -0.19
    jsonp
    -0.19
    ={"/
    -0.19
    ä¸Ńæľī
    -0.19
    POSITIVE LOGITS
     point
    0.40
    çĤ¹
    0.39
    point
    0.32
     Point
    0.32
    Point
    0.32
    éĻĦè¿ij
    0.32
    _point
    0.31
    åľ°çĤ¹
    0.31
    ç»ĪçĤ¹
    0.30
    -point
    0.30
    Activations Density 2.577%

    No Known Activations