© 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-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 89220
    Prev
    Next
    INDEX
    Explanations

    pronouns pointing to others

    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
     Sur
    -0.11
    PD
    -0.11
     witness
    -0.10
     pent
    -0.10
     forcibly
    -0.10
     talking
    -0.10
     Modal
    -0.10
     Integrity
    -0.10
     Ted
    -0.10
     successors
    -0.10
    POSITIVE LOGITS
    Autor
    0.10
     wan
    0.09
     daring
    0.09
     antics
    0.09
    SED
    0.09
     across
    0.09
     ta
    0.08
    /goto
    0.08
    åı¸
    0.08
     flirt
    0.08
    Activations Density 0.008%

    No Known Activations