© 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. 7624
    Prev
    Next
    INDEX
    Explanations

    personal 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
     official
    -0.08
    lite
    -0.08
     Hop
    -0.08
     Horton
    -0.08
     Sor
    -0.07
     rigor
    -0.07
     McL
    -0.07
     coordin
    -0.07
     Wire
    -0.07
     Sab
    -0.07
    POSITIVE LOGITS
    AbsolutePath
    0.11
     cautioned
    0.11
    asma
    0.10
    ander
    0.10
     here
    0.10
     forward
    0.10
     prompted
    0.10
     tent
    0.10
     Beck
    0.10
     couch
    0.10
    Activations Density 0.041%

    No Known Activations