© 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. 57513
    Prev
    Next
    INDEX
    Explanations

    this. member access

    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
    cil
    -0.10
    Dal
    -0.10
     Abr
    -0.10
    LOW
    -0.09
    -authored
    -0.09
    ides
    -0.09
     Dagger
    -0.09
     gep
    -0.09
    gov
    -0.09
    izon
    -0.08
    POSITIVE LOGITS
     inadvert
    0.07
    óa
    0.07
    ull
    0.07
     Candidate
    0.07
     Tier
    0.07
    hall
    0.07
    olis
    0.07
     formations
    0.06
     Cres
    0.06
    ients
    0.06
    Activations Density 0.003%

    No Known Activations