© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 16442
    Prev
    Next
    INDEX
    Explanations

    succulent, succinate, sucrose

    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
    ets
    -0.09
    iores
    -0.09
     Wire
    -0.09
     Budd
    -0.08
    inz
    -0.08
    estar
    -0.08
    nage
    -0.08
    eor
    -0.08
    enden
    -0.08
    wat
    -0.08
    POSITIVE LOGITS
     succ
    0.18
    umbing
    0.14
     Succ
    0.13
    umbed
    0.13
    succ
    0.13
    ulent
    0.13
    inct
    0.12
     prey
    0.11
    rag
    0.10
    antly
    0.10
    Activations Density 0.003%

    No Known Activations