© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 1658
    Prev
    Next
    INDEX
    Explanations

    in [studies/vitro/patients/traditional]

    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
    apped
    -0.09
    oret
    -0.08
     in
    -0.08
    ween
    -0.08
     complete
    -0.07
     town
    -0.07
     proper
    -0.07
     abbiamo
    -0.07
     retard
    -0.07
    stad
    -0.07
    POSITIVE LOGITS
    clusions
    0.18
     accordance
    0.18
    accuracy
    0.16
     relation
    0.15
     conjunction
    0.15
     terms
    0.14
     lieu
    0.14
     vitro
    0.14
    /of
    0.13
     detail
    0.13
    Activations Density 1.922%

    No Known Activations