© 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. 7887
    Prev
    Next
    INDEX
    Explanations

    locations and identifiers

    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
     Columbia
    -0.16
     Tacoma
    -0.15
     Olympia
    -0.15
     Spokane
    -0.14
    Philadelphia
    -0.14
    Seattle
    -0.14
     Mosul
    -0.14
     Alexandria
    -0.14
     Norwegian
    -0.13
     Sic
    -0.13
    POSITIVE LOGITS
     Essex
    0.19
     Maharashtra
    0.17
     Rochester
    0.16
     Pune
    0.15
     Brisbane
    0.14
     polyester
    0.13
     Apache
    0.12
     Queensland
    0.12
     Polyester
    0.12
     Hartford
    0.11
    Activations Density 3.201%

    No Known Activations