© 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. 50096
    Prev
    Next
    INDEX
    Explanations

    determiners and prepositions followed by common words

    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
    jen
    -0.10
     voc
    -0.10
    ragen
    -0.09
    <v
    -0.09
     oltre
    -0.09
     Harris
    -0.09
    apse
    -0.09
     frog
    -0.09
    ateria
    -0.09
    Know
    -0.08
    POSITIVE LOGITS
    oui
    0.07
    czy
    0.07
    ĥģ
    0.06
    âĢ¦↵↵↵↵
    0.06
    ëĭĪëĭ¤
    0.06
     âĢ¦↵↵
    0.06
     perpetr
    0.06
    /List
    0.06
     guarante
    0.06
    elay
    0.06
    Activations Density 3.625%

    No Known Activations