© 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. 1933
    Prev
    Next
    INDEX
    Explanations

    possessive words related to roles

    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
    ))->
    -0.11
    ,get
    -0.11
    -wise
    -0.11
    ])->
    -0.10
     gast
    -0.09
    rame
    -0.09
    \\/
    -0.09
    chein
    -0.09
     choses
    -0.09
    ori
    -0.09
    POSITIVE LOGITS
     regarding
    0.12
     concerning
    0.11
    's
    0.09
    ’s
    0.09
    们
    0.08
     during
    0.08
     coincide
    0.08
     resulting
    0.08
    sen
    0.08
     reflected
    0.08
    Activations Density 2.495%

    No Known Activations