© 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. 50014
    Prev
    Next
    INDEX
    Explanations

    prices and fees

    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
     medals
    -0.09
    atu
    -0.09
     forcing
    -0.09
     <",
    -0.09
     invitations
    -0.08
    aic
    -0.08
    labels
    -0.08
    Compare
    -0.08
     THEIR
    -0.08
     apparently
    -0.08
    POSITIVE LOGITS
     $
    0.16
     fifty
    0.14
     [$
    0.14
     price
    0.13
    :$
    0.12
    PRICE
    0.12
     charge
    0.12
     ¥
    0.12
     Fifty
    0.12
     $__
    0.12
    Activations Density 0.037%

    No Known Activations