© 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. 50094
    Prev
    Next
    INDEX
    Explanations

    dates and time spans

    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
    alis
    -0.10
    zell
    -0.10
    usk
    -0.10
     domin
    -0.09
    ope
    -0.09
    mom
    -0.09
    Animations
    -0.09
     youtube
    -0.09
    ech
    -0.09
     YouTube
    -0.09
    POSITIVE LOGITS
     insignificant
    0.09
     aged
    0.09
    okies
    0.09
     Abb
    0.09
     year
    0.08
     newbie
    0.08
     timing
    0.08
     rounding
    0.08
     Specifications
    0.08
     Invitation
    0.08
    Activations Density 0.029%

    No Known Activations