© 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. 113308
    Prev
    Next
    INDEX
    Explanations

    look for, carrier family, located in, working on, =localhost:port

    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
     rever
    -0.09
     Oslo
    -0.08
    LAB
    -0.08
     Abr
    -0.08
     gra
    -0.07
     otherwise
    -0.07
    929
    -0.07
    gle
    -0.07
    unte
    -0.07
     Beck
    -0.07
    POSITIVE LOGITS
     totalement
    0.10
     vraiment
    0.10
     Equity
    0.10
    eut
    0.10
    ace
    0.10
     sécur
    0.10
     rapidement
    0.10
     conquest
    0.10
     Uph
    0.09
    aison
    0.09
    Activations Density 0.001%

    No Known Activations