© 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. 7251
    Prev
    Next
    INDEX
    Explanations

    sides and positions

    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
    ucci
    -0.09
     hacker
    -0.07
     Lester
    -0.07
     Blackburn
    -0.07
     sme
    -0.07
     Plat
    -0.07
     anyhow
    -0.07
     beforehand
    -0.07
     perman
    -0.07
     trick
    -0.07
    POSITIVE LOGITS
     splitted
    0.13
     equipments
    0.12
    kad
    0.12
     vicinity
    0.12
    enga
    0.12
    /component
    0.11
     shoulders
    0.11
    uries
    0.11
    chema
    0.11
     downwards
    0.11
    Activations Density 0.151%

    No Known Activations