© 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. 14670
    Prev
    Next
    INDEX
    Explanations

    months and years

    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
    为
    -0.11
     penchant
    -0.10
     for
    -0.10
     forever
    -0.10
     длÑı
    -0.10
     premise
    -0.10
    ishes
    -0.10
     pil
    -0.10
     für
    -0.09
    otec
    -0.09
    POSITIVE LOGITS
     sake
    0.44
     purposes
    0.36
     reasons
    0.17
     intents
    0.13
     purpose
    0.12
     PURPOSE
    0.12
    pur
    0.11
     Pur
    0.10
     foreseeable
    0.10
    bidden
    0.10
    Activations Density 2.941%

    No Known Activations