© 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. 50161
    Prev
    Next
    INDEX
    Explanations

    conjunctions and clause starters

    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
     jointly
    -0.18
    ä¸İ
    -0.18
     mutual
    -0.15
     together
    -0.13
     joint
    -0.13
     yourself
    -0.13
     mutually
    -0.13
    joint
    -0.12
    burgh
    -0.12
     shared
    -0.12
    POSITIVE LOGITS
    们
    0.12
     our
    0.09
    utz
    0.09
    æĪij们
    0.09
    They
    0.08
    fait
    0.08
    969
    0.08
    599
    0.08
    tron
    0.08
    keh
    0.08
    Activations Density 0.040%

    No Known Activations