© 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. 112955
    Prev
    Next
    INDEX
    Explanations

    years, months, weeks, days

    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
     dispos
    -0.11
     Disabled
    -0.10
     loos
    -0.10
    bis
    -0.10
     halfway
    -0.10
     lifelong
    -0.10
    rol
    -0.10
    ikh
    -0.10
     Mot
    -0.10
     Hockey
    -0.10
    POSITIVE LOGITS
     already
    0.10
     now
    0.10
     ago
    0.09
     longer
    0.09
    _ER
    0.08
     Eld
    0.08
    fir
    0.08
     scl
    0.08
     accumulating
    0.08
    ago
    0.08
    Activations Density 0.065%

    No Known Activations