© 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. 114109
    Prev
    Next
    INDEX
    Explanations

    cro" 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
    EMPL
    -0.11
     suff
    -0.10
     notions
    -0.09
    usu
    -0.09
     Sle
    -0.09
     slick
    -0.09
     grouping
    -0.08
    bh
    -0.08
     intermediary
    -0.08
    bz
    -0.08
    POSITIVE LOGITS
     cro
    0.14
     Cro
    0.13
    cro
    0.11
    Cro
    0.10
    alles
    0.09
     dok
    0.09
    stadt
    0.08
     uneven
    0.08
    printStats
    0.08
     unde
    0.08
    Activations Density 0.063%

    No Known Activations