© 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. 5241
    Prev
    Next
    INDEX
    Explanations

    1) and 2)

    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
    aze
    -0.09
    umper
    -0.09
     hereby
    -0.09
    esper
    -0.09
     intimid
    -0.09
    cation
    -0.08
     Proj
    -0.08
     Kemp
    -0.08
    astle
    -0.08
     equipments
    -0.08
    POSITIVE LOGITS
     Sinn
    0.11
    .travel
    0.10
    770
    0.09
     Decorating
    0.09
     Sok
    0.09
     sa
    0.09
     Kul
    0.09
    .sa
    0.09
     dedicated
    0.09
    lient
    0.09
    Activations Density 0.013%

    No Known Activations