© 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. 29065
    Prev
    Next
    INDEX
    Explanations

    county names and associated places

    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
     Digit
    -0.11
    uka
    -0.11
     Canc
    -0.11
    mps
    -0.10
    unci
    -0.10
     Strat
    -0.10
     inoc
    -0.10
    si
    -0.10
     travelling
    -0.10
    reste
    -0.10
    POSITIVE LOGITS
     seat
    0.09
     Clerk
    0.08
     seats
    0.08
     McDon
    0.08
    Mahon
    0.08
    pedia
    0.08
    cho
    0.08
     Federation
    0.07
     gent
    0.07
     mer
    0.07
    Activations Density 0.034%

    No Known Activations