© 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. 54628
    Prev
    Next
    INDEX
    Explanations

    first round of

    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
    arda
    -0.08
    /internal
    -0.08
     vet
    -0.08
    ÑĢан
    -0.08
     closely
    -0.08
    Ñĩ
    -0.07
     saturated
    -0.07
    ðŁĴ
    -0.07
    mere
    -0.07
    odox
    -0.07
    POSITIVE LOGITS
     Distrib
    0.10
     +=↵
    0.09
    isd
    0.08
     guarante
    0.08
     Shepard
    0.08
    anche
    0.08
     permalink
    0.08
     Kub
    0.08
    Unhandled
    0.08
     Ju
    0.08
    Activations Density 0.077%

    No Known Activations