© 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. 26087
    Prev
    Next
    INDEX
    Explanations

    come to or from

    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
     Cra
    -0.08
    UTO
    -0.07
    assi
    -0.07
    omo
    -0.07
     sleeping
    -0.07
    ox
    -0.07
    omi
    -0.07
     lax
    -0.07
     Simmons
    -0.07
     greens
    -0.07
    POSITIVE LOGITS
     equipped
    0.13
     unarmed
    0.12
     hail
    0.12
     closest
    0.11
     close
    0.10
     adorned
    0.10
     embody
    0.10
     onClose
    0.10
     sparing
    0.10
     insn
    0.10
    Activations Density 0.039%

    No Known Activations