© 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. 3361
    Prev
    Next
    INDEX
    Explanations

    US states and cities

    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
    .orange
    -0.08
     knack
    -0.08
    è¶
    -0.08
    ãģĵãĤĵ
    -0.08
    ople
    -0.08
    inv
    -0.08
     nett
    -0.08
    iba
    -0.08
     cess
    -0.07
     uptime
    -0.07
    POSITIVE LOGITS
     Sequ
    0.09
    ahi
    0.09
    .aw
    0.09
    rag
    0.09
    idi
    0.08
    ÑĮÑİ
    0.08
     shower
    0.08
     Lama
    0.08
     Hari
    0.08
    uin
    0.08
    Activations Density 0.063%

    No Known Activations