© 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. 91726
    Prev
    Next
    INDEX
    Explanations

    guess what, wonder how

    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
     reap
    -0.09
    kest
    -0.09
    ask
    -0.08
    MER
    -0.08
     blah
    -0.08
    ER
    -0.08
    oha
    -0.08
    des
    -0.08
    :)
    -0.08
    ernet
    -0.07
    POSITIVE LOGITS
    fully
    0.15
    ably
    0.15
    ful
    0.13
    less
    0.11
    ully
    0.11
    buie
    0.10
    able
    0.10
    ibly
    0.10
    edly
    0.10
    Fully
    0.10
    Activations Density 0.045%

    No Known Activations