© 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. 17628
    Prev
    Next
    INDEX
    Explanations

    latitude and longitude coordinates

    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
    adius
    -0.11
    OTA
    -0.10
    ilder
    -0.10
    nika
    -0.10
     screwed
    -0.10
     initialised
    -0.10
    istan
    -0.10
     tk
    -0.10
    cling
    -0.09
    'aff
    -0.09
    POSITIVE LOGITS
     latitude
    0.12
     lat
    0.12
    lat
    0.09
     synchronous
    0.09
     (-
    0.09
    ilon
    0.08
     luz
    0.08
    =-
    0.08
    Latitude
    0.08
    ~-
    0.08
    Activations Density 0.099%

    No Known Activations