© 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. 17759
    Prev
    Next
    INDEX
    Explanations

    months and dates

    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
    chs
    -0.10
     aforementioned
    -0.09
    -question
    -0.09
    gather
    -0.09
     Chim
    -0.09
     sc
    -0.09
    oi
    -0.09
    str
    -0.09
    ade
    -0.09
    dit
    -0.09
    POSITIVE LOGITS
    oku
    0.09
     backstage
    0.09
    ronym
    0.09
     subt
    0.09
     typeid
    0.08
    anic
    0.08
     priv
    0.08
     overt
    0.08
    agic
    0.08
    (ur
    0.08
    Activations Density 0.002%

    No Known Activations