© 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. 17418
    Prev
    Next
    INDEX
    Explanations

    good qualities or characteristics

    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
    /Area
    -0.10
     resil
    -0.10
    antz
    -0.10
     downward
    -0.10
     downwards
    -0.09
     Breitbart
    -0.09
    ampions
    -0.09
     beaut
    -0.09
    rig
    -0.09
     Encore
    -0.09
    POSITIVE LOGITS
     Nice
    0.13
     nice
    0.11
     nic
    0.11
     doc
    0.10
    Nice
    0.10
    nice
    0.10
     clinically
    0.10
     demasi
    0.10
     TOO
    0.10
     Cand
    0.10
    Activations Density 0.016%

    No Known Activations