© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 116951
    Prev
    Next
    INDEX
    Explanations

    conjunctions and sentence connectors

    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
     __________________↵↵
    -0.10
     Edwards
    -0.10
     dsp
    -0.09
     pal
    -0.09
     Toolbox
    -0.09
    olate
    -0.09
    eo
    -0.08
     Palace
    -0.08
    ).__
    -0.08
     dep
    -0.08
    POSITIVE LOGITS
     And
    0.23
    And
    0.23
    and
    0.23
     furthermore
    0.20
    â̦and
    0.20
     especially
    0.19
     however
    0.19
     AND
    0.18
     Or
    0.18
     moreover
    0.18
    Activations Density 0.144%

    No Known Activations