© 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. 47969
    Prev
    Next
    INDEX
    Explanations

    In addition to

    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
    ider
    -0.08
    eka
    -0.07
     Fashion
    -0.06
     Goodman
    -0.06
     cuts
    -0.06
     Preis
    -0.06
    KL
    -0.06
    åī
    -0.06
    upo
    -0.06
    sson
    -0.06
    POSITIVE LOGITS
     terrestrial
    0.18
     adults
    0.17
     earthly
    0.16
     mainland
    0.16
     humans
    0.14
     external
    0.14
     weekdays
    0.14
     Adults
    0.14
     itu
    0.13
    Orm
    0.12
    Activations Density 0.451%

    No Known Activations