© 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. 48797
    Prev
    Next
    INDEX
    Explanations

    something about

    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
     memorable
    -0.11
     notable
    -0.11
     Hanna
    -0.10
    Pel
    -0.10
     Marathon
    -0.10
     Ping
    -0.10
     notice
    -0.09
     Coron
    -0.09
     somewhat
    -0.09
    ices
    -0.09
    POSITIVE LOGITS
     combination
    0.11
     combinations
    0.10
     tone
    0.10
    imson
    0.10
     atmosphere
    0.09
     recl
    0.09
    combination
    0.09
     detached
    0.09
     McCart
    0.09
     timing
    0.08
    Activations Density 0.009%

    No Known Activations