© 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. 33567
    Prev
    Next
    INDEX
    Explanations

    connecting phrases with prepositions/auxiliaries

    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
    -plus
    -0.20
     oft
    -0.14
    -than
    -0.13
    -vers
    -0.13
    /from
    -0.13
     PLUS
    -0.13
    /etc
    -0.13
    -known
    -0.12
    -turned
    -0.12
     nonexistent
    -0.12
    POSITIVE LOGITS
     Miche
    0.15
     ,(
    0.13
     atleast
    0.12
     wich
    0.11
     whats
    0.11
    Lets
    0.11
     ,↵
    0.11
     ,↵↵
    0.11
     frankly
    0.11
     alot
    0.10
    Activations Density 2.347%

    No Known Activations