© 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. 91844
    Prev
    Next
    INDEX
    Explanations

    could be, can be

    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
     would
    -0.12
    fty
    -0.10
     could
    -0.09
    would
    -0.09
     Would
    -0.09
    Brun
    -0.09
    could
    -0.08
    atism
    -0.08
    port
    -0.08
    á»
    -0.08
    POSITIVE LOGITS
    -be
    0.17
     be
    0.16
    ’ve
    0.15
    nt
    0.15
    've
    0.14
    ered
    0.13
    ering
    0.13
    -have
    0.12
    enberg
    0.12
    aq
    0.12
    Activations Density 0.001%

    No Known Activations