© 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. 61591
    Prev
    Next
    INDEX
    Explanations

    assassin, ask, task, askarin

    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
     fam
    -0.09
    HTTPRequest
    -0.08
    /cop
    -0.08
    forth
    -0.08
     cref
    -0.08
    -0.08
    pherd
    -0.07
    bundles
    -0.07
    lopedia
    -0.07
    åĥ
    -0.07
    POSITIVE LOGITS
    isson
    0.10
    coc
    0.09
    idas
    0.09
     somewhere
    0.09
    TW
    0.09
     prolific
    0.09
    heel
    0.09
    otine
    0.09
    ints
    0.09
     jew
    0.08
    Activations Density 0.055%

    No Known Activations