© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 31597
    Prev
    Next
    INDEX
    Explanations

    reading time

    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
     fres
    -0.09
     Fist
    -0.08
     accept
    -0.08
    endregion
    -0.08
     gyr
    -0.08
     visc
    -0.08
    vos
    -0.07
    ardon
    -0.07
     Fres
    -0.07
     analytic
    -0.07
    POSITIVE LOGITS
    âĦ
    0.12
    ordin
    0.11
    ald
    0.10
    573
    0.10
     time
    0.10
     leisure
    0.10
     BOT
    0.09
     Enums
    0.09
     prep
    0.09
     poo
    0.09
    Activations Density 0.004%

    No Known Activations