© 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. 49462
    Prev
    Next
    INDEX
    Explanations

    in phrases like "in fact"

    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
    xmax
    -0.09
    anza
    -0.09
     gren
    -0.09
     cheered
    -0.09
     Barg
    -0.08
    ITT
    -0.08
     Schul
    -0.08
     vd
    -0.08
    aan
    -0.08
     RESP
    -0.08
    POSITIVE LOGITS
     fact
    0.13
    fortunately
    0.11
     which
    0.11
     hindsight
    0.10
     contrary
    0.10
     although
    0.10
    complete
    0.10
     fortunately
    0.10
     once
    0.10
    once
    0.09
    Activations Density 0.198%

    No Known Activations