© 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. 7255
    Prev
    Next
    INDEX
    Explanations

    workers, performers, companies, athletes, printers, designers

    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
     therein
    -0.10
    bec
    -0.10
     Bec
    -0.10
     Haw
    -0.09
     becomes
    -0.09
     becoming
    -0.09
     behaved
    -0.09
     remains
    -0.09
     contributed
    -0.09
     now
    -0.09
    POSITIVE LOGITS
     typically
    0.16
     tend
    0.13
     oft
    0.13
     spend
    0.13
     often
    0.13
     NEED
    0.12
    typically
    0.12
     spends
    0.12
     Typically
    0.11
     Birch
    0.11
    Activations Density 0.110%

    No Known Activations