© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 33910
    Prev
    Next
    INDEX
    Explanations

    is followed by determiner or pronoun

    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
    icie
    -0.13
     fing
    -0.12
    /change
    -0.12
     Bab
    -0.11
     Uhr
    -0.11
    ouve
    -0.11
    Newsletter
    -0.11
    uil
    -0.11
    agogue
    -0.11
    ky
    -0.11
    POSITIVE LOGITS
    wav
    0.09
     undoubtedly
    0.08
     ability
    0.08
    ardi
    0.08
     introdu
    0.07
     unique
    0.07
    ocus
    0.07
    holm
    0.07
    EF
    0.07
     unquestion
    0.07
    Activations Density 0.013%

    No Known Activations