© 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. 47860
    Prev
    Next
    INDEX
    Explanations

    USA

    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
     powering
    -0.10
    aurus
    -0.09
    oda
    -0.09
    ,
    -0.09
     dining
    -0.08
     goodbye
    -0.08
     crossing
    -0.08
    optic
    -0.08
    fox
    -0.08
    AMS
    -0.08
    POSITIVE LOGITS
    reh
    0.09
    olla
    0.08
     mains
    0.08
    äge
    0.08
    icast
    0.08
    illes
    0.08
    mdi
    0.08
     Indo
    0.08
     USA
    0.08
     FR
    0.08
    Activations Density 0.552%

    No Known Activations