© 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. 6493
    Prev
    Next
    INDEX
    Explanations

    system and its related context

    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
     flick
    -0.08
     Hob
    -0.08
    lich
    -0.08
     Rams
    -0.08
     McCorm
    -0.07
    ger
    -0.07
     Ivanka
    -0.07
    appa
    -0.07
     instrument
    -0.07
     Costume
    -0.07
    POSITIVE LOGITS
     subsystem
    0.30
    (system
    0.28
    /system
    0.25
    System
    0.25
     System
    0.24
     system
    0.23
    /System
    0.23
    Subsystem
    0.22
    SYSTEM
    0.22
    -system
    0.22
    Activations Density 0.800%

    No Known Activations