© 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. 90974
    Prev
    Next
    INDEX
    Explanations

    and blood, communication, information, industrial, neuro, gas

    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
    .JPanel
    -0.13
    olec
    -0.12
    illon
    -0.12
    967
    -0.11
    æĢ§
    -0.10
    _NUMERIC
    -0.10
     powered
    -0.10
    abin
    -0.10
     theoret
    -0.10
     Rape
    -0.10
    POSITIVE LOGITS
     ember
    0.07
     clad
    0.07
     Carp
    0.07
    dfs
    0.07
     gravid
    0.07
     morphology
    0.07
     onCreate
    0.07
     plumbing
    0.07
     carp
    0.07
    -awesome
    0.07
    Activations Density 1.599%

    No Known Activations