© 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. 46923
    Prev
    Next
    INDEX
    Explanations

    prepositions and conjunctions

    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
     underside
    -0.13
     lips
    -0.11
     pores
    -0.11
     bruises
    -0.11
     wounds
    -0.11
     lining
    -0.10
     HAPP
    -0.10
     Curtain
    -0.10
     Hak
    -0.10
     stitches
    -0.10
    POSITIVE LOGITS
     stripped
    0.10
    holm
    0.10
     dining
    0.09
     spur
    0.09
     spont
    0.09
     decom
    0.09
     taboo
    0.08
     Objects
    0.08
    ohan
    0.08
    rew
    0.08
    Activations Density 0.062%

    No Known Activations