© 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. 57214
    Prev
    Next
    INDEX
    Explanations

    film or computer

    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
     Wr
    -0.09
     Braz
    -0.09
     Pret
    -0.08
     finances
    -0.08
     dressing
    -0.07
    ãĤ¹ãĥĪ
    -0.07
     pret
    -0.07
    allet
    -0.07
     Barg
    -0.07
     fruit
    -0.07
    POSITIVE LOGITS
     envisioned
    0.11
     Lifetime
    0.11
    gov
    0.10
    .fields
    0.10
    linger
    0.10
     Organisation
    0.10
    acz
    0.10
    ÑĥÑī
    0.10
     Governance
    0.10
    cline
    0.10
    Activations Density 0.110%

    No Known Activations