© 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. 54589
    Prev
    Next
    INDEX
    Explanations

    tax cuts and increases

    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
     contro
    -0.11
    /man
    -0.10
     developing
    -0.09
     FORCE
    -0.08
    elter
    -0.08
     financially
    -0.08
    (By
    -0.08
     Venom
    -0.08
    iez
    -0.08
     supervised
    -0.08
    POSITIVE LOGITS
    bek
    0.09
    ouser
    0.09
    iffe
    0.09
    alse
    0.09
    rah
    0.09
     targeting
    0.08
     hod
    0.08
     prescriptions
    0.08
     Camp
    0.08
    ست
    0.08
    Activations Density 0.011%

    No Known Activations