© 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. 28041
    Prev
    Next
    INDEX
    Explanations

    missing persons, links, values, or elements

    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
    hof
    -0.08
    vis
    -0.08
    ubo
    -0.08
    jc
    -0.08
    ares
    -0.08
    800
    -0.08
     weakening
    -0.08
    865
    -0.07
    beck
    -0.07
     abandon
    -0.07
    POSITIVE LOGITS
     missing
    0.21
    missing
    0.18
     Missing
    0.18
    Missing
    0.17
     MISSING
    0.16
     presumed
    0.15
    ees
    0.14
     persons
    0.14
     Persons
    0.14
     link
    0.13
    Activations Density 0.054%

    No Known Activations