© 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. 28203
    Prev
    Next
    INDEX
    Explanations

    copyright and license

    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
     Gilbert
    -0.10
    cart
    -0.09
     terse
    -0.09
    chter
    -0.09
     Gil
    -0.09
     Sons
    -0.09
    ’T
    -0.09
     libido
    -0.09
     bif
    -0.08
    Contrib
    -0.08
    POSITIVE LOGITS
     defaults
    0.11
    hare
    0.10
    eed
    0.09
    CID
    0.09
     Gazette
    0.09
    ils
    0.09
     afterwards
    0.09
     cap
    0.09
    rip
    0.09
    .(
    0.09
    Activations Density 0.001%

    No Known Activations