© 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. 28822
    Prev
    Next
    INDEX
    Explanations

    prepositions and place names

    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
     Sue
    -0.10
     irres
    -0.07
     "...
    -0.07
     Sid
    -0.07
     Dale
    -0.07
    ourd
    -0.07
     PÃ¥
    -0.07
    bee
    -0.07
     -↵↵
    -0.07
     ~~
    -0.07
    POSITIVE LOGITS
     Kart
    0.12
     fert
    0.11
    bart
    0.11
    slaught
    0.11
     reb
    0.11
    tit
    0.10
    \$
    0.10
     Bust
    0.10
     barr
    0.10
    ataka
    0.10
    Activations Density 0.017%

    No Known Activations