© 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. 4186
    Prev
    Next
    INDEX
    Explanations

    all times

    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
     routinely
    -0.13
     everytime
    -0.12
     regularly
    -0.11
     altogether
    -0.11
    omp
    -0.11
     Guth
    -0.11
    reh
    -0.10
    Slf
    -0.10
     overall
    -0.10
    lege
    -0.10
    POSITIVE LOGITS
    unte
    0.10
    jours
    0.08
    adal
    0.08
    /all
    0.08
     stamp
    0.08
     punitive
    0.08
     disob
    0.08
    -available
    0.08
    (!
    0.08
     stamps
    0.08
    Activations Density 0.033%

    No Known Activations