© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 17650
    Prev
    Next
    INDEX
    Explanations

    starts of new phrases capitalized

    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
     *"
    -0.08
    enth
    -0.08
    /ion
    -0.08
    lion
    -0.08
    zb
    -0.08
    obi
    -0.08
     Hep
    -0.08
    encia
    -0.07
     rest
    -0.07
    abi
    -0.07
    POSITIVE LOGITS
    lluminate
    0.09
     blink
    0.09
    venue
    0.09
     uniformly
    0.09
    (_:
    0.09
    unfold
    0.09
    .LA
    0.09
     MemoryStream
    0.09
    arcer
    0.09
     waged
    0.09
    Activations Density 0.010%

    No Known Activations