© 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. 117094
    Prev
    Next
    INDEX
    Explanations

    disc prefixes

    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
    est
    -0.10
    ters
    -0.10
    cool
    -0.10
     cuff
    -0.09
     Strap
    -0.08
    eer
    -0.08
    liest
    -0.08
    lest
    -0.08
    o
    -0.08
    ths
    -0.08
    POSITIVE LOGITS
    olor
    0.16
    arding
    0.14
    iplina
    0.13
    ursive
    0.13
    riminator
    0.12
    ipline
    0.12
    ursively
    0.12
    iplinary
    0.12
    ourses
    0.11
    ussions
    0.11
    Activations Density 0.144%

    No Known Activations