© 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. 49116
    Prev
    Next
    INDEX
    Explanations

    available and ready

    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
     Shak
    -0.10
    lag
    -0.09
     honeymoon
    -0.09
    adt
    -0.08
    oli
    -0.08
     Zus
    -0.08
     Lockheed
    -0.08
    endor
    -0.08
    adc
    -0.08
     meas
    -0.08
    POSITIVE LOGITS
     ready
    0.46
     available
    0.38
     availability
    0.38
     readiness
    0.37
    ready
    0.35
     Ready
    0.35
     Available
    0.34
     Availability
    0.33
     READY
    0.32
    Ready
    0.31
    Activations Density 0.199%

    No Known Activations