© 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. 112664
    Prev
    Next
    INDEX
    Explanations

    studied and sought

    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
     cool
    -0.10
    kat
    -0.09
     pairwise
    -0.09
     tailored
    -0.08
    apel
    -0.08
    uku
    -0.08
    ISM
    -0.08
    334
    -0.08
    gain
    -0.08
    ure
    -0.08
    POSITIVE LOGITS
    -about
    0.13
     misunderstood
    0.13
     searched
    0.12
     scrutin
    0.12
    ographed
    0.12
    ted
    0.12
    -after
    0.11
    ned
    0.11
    ited
    0.11
     ones
    0.11
    Activations Density 0.167%

    No Known Activations