© 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-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 114614
    Prev
    Next
    INDEX
    Explanations

    possessive pronoun before noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    amel
    -0.13
    bam
    -0.12
    enen
    -0.11
     Poz
    -0.11
    HOOK
    -0.11
    bru
    -0.11
    ullo
    -0.10
     ourselves
    -0.10
     erk
    -0.10
    uers
    -0.10
    POSITIVE LOGITS
     their
    0.13
     clients
    0.13
     his
    0.12
     flagship
    0.11
     product
    0.11
     leurs
    0.11
     client
    0.10
     creations
    0.10
     seu
    0.10
     customers
    0.09
    Activations Density 0.891%

    No Known Activations