© 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. 57296
    Prev
    Next
    INDEX
    Explanations

    survey data collection

    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
     mentors
    -0.09
    arin
    -0.09
     upstream
    -0.08
     downstream
    -0.08
    iod
    -0.08
    avin
    -0.08
    gre
    -0.07
    aring
    -0.07
     incentives
    -0.07
    ós
    -0.07
    POSITIVE LOGITS
     questionnaire
    0.11
     refreshed
    0.11
     proportions
    0.10
     interviewing
    0.10
     proport
    0.10
     simul
    0.09
     confidentiality
    0.09
    bill
    0.09
     interview
    0.09
     Enumerator
    0.09
    Activations Density 0.072%

    No Known Activations