© 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. 3523
    Prev
    Next
    INDEX
    Explanations

    -effect devices, ucidating

    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
    ,!
    -0.14
    INES
    -0.11
    abad
    -0.10
    ["_
    -0.10
    lox
    -0.10
    iped
    -0.10
    apg
    -0.10
    µ¬
    -0.10
    .Br
    -0.10
    ensch
    -0.10
    POSITIVE LOGITS
    Âł
    0.08
    ->
    0.08
    -of
    0.07
    duk
    0.07
    dit
    0.07
    &
    0.06
     Roy
    0.06
     Ang
    0.06
    cee
    0.06
     "
    0.06
    Activations Density 0.021%

    No Known Activations