© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 113498
    Prev
    Next
    INDEX
    Explanations

    location or time preposition followed by determiners

    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
    urg
    -0.12
    reds
    -0.11
     stav
    -0.11
    ummer
    -0.11
    allest
    -0.11
    accum
    -0.10
    rium
    -0.10
    urgy
    -0.10
    omb
    -0.10
    agy
    -0.10
    POSITIVE LOGITS
     Kiss
    0.09
     weekdays
    0.07
     prohibit
    0.06
     kiss
    0.06
     Interracial
    0.06
     these
    0.06
    pedia
    0.06
    411
    0.06
    azor
    0.06
     colleg
    0.06
    Activations Density 0.426%

    No Known Activations