© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 113467
    Prev
    Next
    INDEX
    Explanations

    that our

    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
    ìĥ
    -0.10
    enson
    -0.09
     otherwise
    -0.09
    ensa
    -0.09
    ensen
    -0.08
    olia
    -0.08
     always
    -0.08
     whereas
    -0.08
    imas
    -0.08
    affer
    -0.08
    POSITIVE LOGITS
     things
    0.13
     we
    0.12
     Things
    0.12
     suspicions
    0.10
    Things
    0.10
     realized
    0.10
     ...↵↵↵↵
    0.10
     realise
    0.09
     eyebrows
    0.09
     resembl
    0.09
    Activations Density 0.019%

    No Known Activations