© 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. 3328
    Prev
    Next
    INDEX
    Explanations

    technical descriptions

    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
    @if
    -0.08
    Universal
    -0.07
    roz
    -0.07
    cle
    -0.07
     subtly
    -0.07
    omm
    -0.07
    IFn
    -0.07
     nell
    -0.07
    ific
    -0.06
    rios
    -0.06
    POSITIVE LOGITS
     classified
    0.11
     adjective
    0.11
     truly
    0.10
    atti
    0.10
     lock
    0.10
     Truly
    0.10
     McLaren
    0.09
     Knox
    0.09
     opting
    0.09
     qualifies
    0.09
    Activations Density 0.986%

    No Known Activations