© 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. 49306
    Prev
    Next
    INDEX
    Explanations

    company legal suffixes

    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
     sod
    -0.10
     Vera
    -0.10
     pit
    -0.10
    qui
    -0.09
     chuck
    -0.09
     curt
    -0.09
    ural
    -0.09
     (!!
    -0.09
    ilon
    -0.09
     Enrique
    -0.09
    POSITIVE LOGITS
     db
    0.14
    dba
    0.13
     subsidiary
    0.13
    .,
    0.12
    opor
    0.11
     DB
    0.11
     BBB
    0.10
     Liability
    0.10
     Registered
    0.09
     d
    0.09
    Activations Density 0.682%

    No Known Activations