© 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. 30166
    Prev
    Next
    INDEX
    Explanations

    Precedential or Non-Precedential

    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
    /cop
    -0.12
    op
    -0.10
    -Semit
    -0.10
     Wien
    -0.10
     Analyzer
    -0.10
    atat
    -0.10
     Compound
    -0.10
     Labs
    -0.10
     Wolff
    -0.10
     knowingly
    -0.10
    POSITIVE LOGITS
     extrad
    0.09
     Westbrook
    0.09
    ama
    0.08
     Appointment
    0.08
     extradition
    0.08
     booked
    0.08
     upstairs
    0.07
     cst
    0.07
    YYY
    0.07
     intermittent
    0.07
    Activations Density 0.001%

    No Known Activations