© 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. 88720
    Prev
    Next
    INDEX
    Explanations

    for followed by pronouns

    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
    /th
    -0.09
    ots
    -0.09
    ,it
    -0.09
    627
    -0.09
    oci
    -0.09
     Nab
    -0.09
    infinity
    -0.08
     Tw
    -0.08
    aire
    -0.08
    à¸ģาร
    -0.08
    POSITIVE LOGITS
     us
    0.19
     them
    0.15
     me
    0.14
     someone
    0.13
     him
    0.12
    them
    0.10
     bystand
    0.09
     Someone
    0.09
    usher
    0.09
     alguien
    0.09
    Activations Density 0.081%

    No Known Activations