© 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. 17695
    Prev
    Next
    INDEX
    Explanations

    Southern and Northwestern regions

    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
    ocz
    -0.09
    usc
    -0.09
     Castro
    -0.09
    bil
    -0.09
    oci
    -0.08
     Resorts
    -0.08
     Gand
    -0.08
    utow
    -0.08
    avr
    -0.08
    yen
    -0.08
    POSITIVE LOGITS
    -east
    0.22
     hemisphere
    0.21
    -west
    0.20
    most
    0.20
     Hemisphere
    0.19
    ward
    0.18
    bound
    0.18
    ern
    0.18
    wards
    0.17
    -central
    0.17
    Activations Density 0.249%

    No Known Activations