© 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. 57906
    Prev
    Next
    INDEX
    Explanations

    policy after historical events

    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
     pioneers
    -0.10
     presumably
    -0.09
    ylon
    -0.09
    -lib
    -0.08
    Ñħодим
    -0.08
     revolutionary
    -0.08
     liberated
    -0.08
     pioneering
    -0.08
     trag
    -0.08
    ftar
    -0.08
    POSITIVE LOGITS
    lei
    0.10
    ecret
    0.09
     intercept
    0.09
     Brace
    0.09
     ridge
    0.08
    .kode
    0.08
    isz
    0.08
    paste
    0.08
     Kron
    0.08
     Pap
    0.08
    Activations Density 0.014%

    No Known Activations