© 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. 32182
    Prev
    Next
    INDEX
    Explanations

    frequent occurrences

    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
     Faul
    -0.10
    hawks
    -0.10
     dread
    -0.09
     seriousness
    -0.09
    ugin
    -0.09
    bjerg
    -0.09
    creen
    -0.09
    backs
    -0.09
    leen
    -0.08
    izations
    -0.08
    POSITIVE LOGITS
     Asked
    0.17
    emente
    0.15
    ily
    0.14
    çİĩ
    0.11
    ely
    0.10
    antly
    0.10
     flyer
    0.10
     enough
    0.10
     occurrence
    0.10
    -inverse
    0.10
    Activations Density 0.040%

    No Known Activations