© 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. 16033
    Prev
    Next
    INDEX
    Explanations

    with or without

    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
     ise
    -0.11
     Nie
    -0.11
     Conce
    -0.11
    Nie
    -0.10
    ises
    -0.10
    arge
    -0.10
     Mitch
    -0.10
    InstanceOf
    -0.10
    SEP
    -0.10
    ardin
    -0.10
    POSITIVE LOGITS
     without
    0.28
     with
    0.25
    without
    0.21
     WITHOUT
    0.20
     via
    0.18
    with
    0.17
     Without
    0.17
     through
    0.16
     anonymously
    0.15
    Without
    0.15
    Activations Density 0.536%

    No Known Activations