© 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. 28058
    Prev
    Next
    INDEX
    Explanations

    as 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
    ogl
    -0.10
    vn
    -0.09
     fore
    -0.09
    cona
    -0.09
    CTR
    -0.09
     Mn
    -0.09
    IEL
    -0.09
     Ann
    -0.09
    brick
    -0.09
    uin
    -0.09
    POSITIVE LOGITS
     they
    0.15
     she
    0.11
     he
    0.10
     kel
    0.10
     lay
    0.10
     latter
    0.10
     it
    0.09
    semb
    0.09
    inton
    0.09
    ham
    0.09
    Activations Density 0.132%

    No Known Activations