© 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. 3568
    Prev
    Next
    INDEX
    Explanations

    quantities or groups

    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
    TW
    -0.09
     Quarterly
    -0.08
    .urlopen
    -0.08
    oc
    -0.08
    amin
    -0.08
    pliers
    -0.08
    ingo
    -0.07
    opsy
    -0.07
    Pri
    -0.07
     suicide
    -0.07
    POSITIVE LOGITS
    ampus
    0.12
    hq
    0.09
     blanc
    0.09
     Blanc
    0.09
     Rut
    0.09
    gang
    0.09
     multipart
    0.08
     bes
    0.08
    ODO
    0.08
     comp
    0.08
    Activations Density 0.606%

    No Known Activations