© 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. 4038
    Prev
    Next
    INDEX
    Explanations

    persons to whom

    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
     accompanying
    -0.12
     somebody
    -0.10
     independ
    -0.10
     materially
    -0.10
    moid
    -0.10
    amax
    -0.10
     corresponding
    -0.09
    hetto
    -0.09
    roupon
    -0.09
    arb
    -0.09
    POSITIVE LOGITS
    rio
    0.08
     whom
    0.08
    çĻ
    0.08
    abb
    0.08
    opo
    0.07
     multiple
    0.07
    åıij
    0.07
     spectrum
    0.07
    uk
    0.07
    who
    0.07
    Activations Density 0.339%

    No Known Activations