© 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. 17479
    Prev
    Next
    INDEX
    Explanations

    months and days

    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
     inaug
    -0.12
     Bookmark
    -0.11
    eras
    -0.11
     Flour
    -0.11
     inaugur
    -0.10
    udi
    -0.10
     wand
    -0.10
     Consent
    -0.10
     russe
    -0.10
     :↵↵↵↵
    -0.10
    POSITIVE LOGITS
     Dec
    0.08
    izin
    0.07
     Laden
    0.07
    jom
    0.07
     Berry
    0.07
     enabling
    0.07
     Carlson
    0.07
    bbe
    0.07
     Pac
    0.07
    orest
    0.07
    Activations Density 0.007%

    No Known Activations