© 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. 2368
    Prev
    Next
    INDEX
    Explanations

    names and numbers

    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
    SqlCommand
    -0.24
    ;charset
    -0.24
    "group
    -0.23
    ourke
    -0.22
    æk
    -0.21
    :maj
    -0.20
    utow
    -0.20
     ra
    -0.19
     UCS
    -0.19
    é««
    -0.19
    POSITIVE LOGITS
    "crypto
    0.20
    imore
    0.20
    .masksToBounds
    0.19
    åı¯æĥ³
    0.19
    æĻ¡
    0.18
    _POINTER
    0.18
    åį°è±¡æ·±åĪ»
    0.18
    .YEAR
    0.18
    è¦ģè¿Ľä¸ĢæŃ¥
    0.18
     explan
    0.18
    Activations Density 0.001%

    No Known Activations