© 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. 89507
    Prev
    Next
    INDEX
    Explanations

    Elliot, Ellsworth, Elliott

    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
    quel
    -0.09
    licher
    -0.08
    asco
    -0.08
    eding
    -0.08
    ingo
    -0.08
    ynos
    -0.08
     Rut
    -0.08
    itive
    -0.07
    lest
    -0.07
    AML
    -0.07
    POSITIVE LOGITS
    swer
    0.13
    abeth
    0.13
     Elli
    0.12
    象
    0.12
    ipsoid
    0.11
    ipsis
    0.11
    endale
    0.11
     astronom
    0.11
    sworth
    0.11
    usive
    0.11
    Activations Density 0.021%

    No Known Activations