© 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. 27111
    Prev
    Next
    INDEX
    Explanations

    marked, marking, marks

    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
    IONS
    -0.10
    wi
    -0.08
     Hamp
    -0.08
     Weed
    -0.08
    ions
    -0.08
    wie
    -0.08
    seau
    -0.08
    aze
    -0.08
    parable
    -0.08
    nda
    -0.08
    POSITIVE LOGITS
    .parametrize
    0.20
    eted
    0.17
    /mark
    0.15
     marking
    0.14
    graf
    0.14
    eters
    0.14
    etable
    0.13
    edly
    0.13
    ETING
    0.13
    itecture
    0.13
    Activations Density 0.050%

    No Known Activations