© 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. 3037
    Prev
    Next
    INDEX
    Explanations

    pronouns referring to people

    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
     Furn
    -0.10
    arlo
    -0.10
    icken
    -0.09
    icone
    -0.09
     Moff
    -0.08
    OWER
    -0.08
     Ingram
    -0.08
    itta
    -0.08
    alled
    -0.08
     Hide
    -0.08
    POSITIVE LOGITS
     busiest
    0.08
    lag
    0.08
    ega
    0.08
    egas
    0.08
    asting
    0.08
    gis
    0.07
    merc
    0.07
     AND
    0.07
     AIS
    0.07
    ng
    0.07
    Activations Density 0.145%

    No Known Activations