© 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. 3787
    Prev
    Next
    INDEX
    Explanations

    Type

    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
    ç±»åŀĭçļĦ
    -0.35
    /type
    -0.34
    ç±»åŀĭ
    -0.31
     type
    -0.31
    type
    -0.29
     types
    -0.29
    _type
    -0.26
     Type
    -0.26
    "type
    -0.26
    ehicle
    -0.25
    POSITIVE LOGITS
    paralleled
    0.24
    hattan
    0.22
     nächste
    0.22
    ORM
    0.22
    éĵ
    0.22
     Höhe
    0.21
     automát
    0.21
     moduleId
    0.21
    ç»Ĺ
    0.21
     pestic
    0.20
    Activations Density 0.102%

    No Known Activations