© 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. 54422
    Prev
    Next
    INDEX
    Explanations

    additional components

    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
    vit
    -0.08
     manual
    -0.08
     manually
    -0.07
     tedious
    -0.07
     prohibit
    -0.07
    vet
    -0.06
     symbolic
    -0.06
     luck
    -0.06
    abaj
    -0.06
     cumbersome
    -0.06
    POSITIVE LOGITS
    izi
    0.11
     libertine
    0.11
    lij
    0.10
     fret
    0.10
     Mature
    0.10
    agas
    0.10
    æº
    0.10
     bidding
    0.10
    uala
    0.10
     appar
    0.10
    Activations Density 0.036%

    No Known Activations