© 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. 114084
    Prev
    Next
    INDEX
    Explanations

    URLs with /edit

    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
     Becker
    -0.09
    ses
    -0.08
     Barcl
    -0.08
    noc
    -0.07
     Lima
    -0.07
     onboard
    -0.07
     Cros
    -0.07
    ect
    -0.07
     appreciated
    -0.07
     instituted
    -0.07
    POSITIVE LOGITS
    /edit
    0.13
     Pulse
    0.11
    aland
    0.11
    =.
    0.10
     Deborah
    0.10
    _wc
    0.10
    orsi
    0.10
     Contents
    0.10
    rica
    0.10
    owl
    0.10
    Activations Density 0.042%

    No Known Activations