© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 48331
    Prev
    Next
    INDEX
    Explanations

    une, una, UNE, unequal

    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
    rollo
    -0.10
     Ding
    -0.10
    ling
    -0.10
     breeze
    -0.10
    iding
    -0.10
    _assoc
    -0.09
     freeing
    -0.09
    966
    -0.08
    ensi
    -0.08
     destabil
    -0.08
    POSITIVE LOGITS
    iek
    0.11
    ilia
    0.10
     Baz
    0.09
    urn
    0.09
    ably
    0.09
    fully
    0.09
    astr
    0.09
    CDATA
    0.09
    anse
    0.08
     reluct
    0.08
    Activations Density 0.005%

    No Known Activations