© 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. 54568
    Prev
    Next
    INDEX
    Explanations

    shelf-life

    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
    ions
    -0.11
    led
    -0.10
    ities
    -0.09
    itives
    -0.09
    itive
    -0.09
    .bd
    -0.08
     Kenn
    -0.08
    PED
    -0.08
    gid
    -0.08
    ged
    -0.08
    POSITIVE LOGITS
    ertz
    0.10
    еÑģ
    0.09
    ett
    0.09
     apl
    0.08
    æĪ
    0.08
     Nim
    0.08
    aux
    0.08
    ETYPE
    0.08
    ubar
    0.08
    bw
    0.08
    Activations Density 0.005%

    No Known Activations