© 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. 30609
    Prev
    Next
    INDEX
    Explanations

    names of people

    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
     Papa
    -0.08
     Prince
    -0.08
     King
    -0.07
     Snape
    -0.07
     Princess
    -0.07
     Ober
    -0.07
    Queen
    -0.07
     Deadpool
    -0.07
     Lady
    -0.07
     Dmitry
    -0.06
    POSITIVE LOGITS
     Mark
    0.13
    Mark
    0.12
     Ally
    0.12
    zac
    0.11
    zung
    0.11
     Tome
    0.11
     Pru
    0.11
    beth
    0.11
    edback
    0.11
    -Mart
    0.11
    Activations Density 0.187%

    No Known Activations