© 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. 47483
    Prev
    Next
    INDEX
    Explanations

    common words

    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
     differently
    -0.11
    _different
    -0.11
     different
    -0.11
     solely
    -0.10
    Different
    -0.10
    anton
    -0.10
     strictly
    -0.10
     varied
    -0.10
    different
    -0.10
     Different
    -0.09
    POSITIVE LOGITS
     common
    0.30
     universal
    0.29
     universally
    0.28
     certain
    0.25
     Certain
    0.22
    /common
    0.22
    COMMON
    0.22
    universal
    0.22
     COMMON
    0.21
    common
    0.21
    Activations Density 0.244%

    No Known Activations