© 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. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 55057
    Prev
    Next
    INDEX
    Explanations

    URL components and encoded strings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/olmo-3-saes/olmo-3-1025-7b
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hog
    -0.11
    hon
    -0.10
    auce
    -0.10
    ness
    -0.09
    lav
    -0.09
    .GroupLayout
    -0.09
    endale
    -0.09
    hoa
    -0.09
    HING
    -0.09
    /up
    -0.09
    POSITIVE LOGITS
     unf
    0.09
     bay
    0.08
    Ļ
    0.08
     Thur
    0.08
     Marvel
    0.08
     Kom
    0.08
     Rust
    0.08
     Chamber
    0.08
     Carter
    0.07
     Swift
    0.07
    Activations Density 0.011%

    No Known Activations