© 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. 115503
    Prev
    Next
    INDEX
    Explanations

    revel, manifest, herald

    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
    ef
    -0.10
    lid
    -0.10
    lashes
    -0.09
    ulp
    -0.09
    mia
    -0.08
    ups
    -0.08
    l
    -0.08
    ee
    -0.08
    ños
    -0.08
    reads
    -0.08
    POSITIVE LOGITS
    atory
    0.17
    ations
    0.15
     enjoyment
    0.14
    ation
    0.13
    ries
    0.12
     revel
    0.11
    aed
    0.11
    aes
    0.11
    atio
    0.11
    ously
    0.11
    Activations Density 0.003%

    No Known Activations