© 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. 33708
    Prev
    Next
    INDEX
    Explanations

    time for or to

    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
     rap
    -0.11
    eka
    -0.10
     Hunger
    -0.10
    athe
    -0.10
    aton
    -0.10
    (spec
    -0.09
    SEE
    -0.09
    umba
    -0.09
     Yo
    -0.09
     Lions
    -0.09
    POSITIVE LOGITS
     for
    0.09
    ble
    0.09
     Burnett
    0.09
     to
    0.09
     nowadays
    0.09
     mang
    0.08
     Kemp
    0.08
     Bian
    0.08
    rek
    0.08
     еÑģÑĤÑĮ
    0.08
    Activations Density 0.029%

    No Known Activations