© 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. 33290
    Prev
    Next
    INDEX
    Explanations

    numbers following initial letters

    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
     Bett
    -0.11
     hele
    -0.10
     Savage
    -0.09
    hood
    -0.09
     worship
    -0.09
    iz
    -0.08
     standardized
    -0.08
    auc
    -0.08
    Tur
    -0.08
     Couple
    -0.08
    POSITIVE LOGITS
    ogui
    0.08
     Bru
    0.07
     Rug
    0.07
     Carp
    0.07
     bye
    0.07
     impl
    0.07
     Moo
    0.07
     opport
    0.07
     ah
    0.07
     perfor
    0.07
    Activations Density 0.407%

    No Known Activations