© 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. 57295
    Prev
    Next
    INDEX
    Explanations

    names followed by initials or periods

    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
    Fuse
    -0.08
     Sommer
    -0.07
     Vertical
    -0.07
    soap
    -0.07
    ÑĤÑĥ
    -0.07
     Geld
    -0.07
    ampler
    -0.07
    ãĤ¦
    -0.06
     straw
    -0.06
    abad
    -0.06
    POSITIVE LOGITS
    ritten
    0.11
     GRAT
    0.10
    erno
    0.10
    ILI
    0.09
     {!
    0.09
     alm
    0.09
    ahn
    0.09
    .multi
    0.09
    ï¿
    0.09
    ucci
    0.08
    Activations Density 0.030%

    No Known Activations