© 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. 54470
    Prev
    Next
    INDEX
    Explanations

    android package attributes

    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
     Emerald
    -0.09
    far
    -0.09
     Rif
    -0.09
     Mitch
    -0.08
     alc
    -0.08
     sabotage
    -0.08
    tail
    -0.08
    chez
    -0.08
    -ui
    -0.08
    shal
    -0.08
    POSITIVE LOGITS
    resa
    0.11
    ernet
    0.10
     bid
    0.09
    ;br
    0.08
    ashi
    0.08
    alo
    0.08
    ustin
    0.08
    aspers
    0.08
     sweetheart
    0.08
    imson
    0.08
    Activations Density 0.006%

    No Known Activations