© 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. 111851
    Prev
    Next
    INDEX
    Explanations

    protestsunrestchaos

    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
     excess
    -0.11
     flashing
    -0.10
     dissoci
    -0.10
     shining
    -0.10
     smiling
    -0.10
     blinking
    -0.10
     dripping
    -0.10
    715
    -0.10
     Victims
    -0.10
    ople
    -0.10
    POSITIVE LOGITS
     upro
    0.21
     erupted
    0.20
     collectively
    0.19
     murm
    0.18
     chatter
    0.18
     erupt
    0.17
     chaos
    0.17
     collective
    0.17
     eruption
    0.17
     unrest
    0.16
    Activations Density 0.072%

    No Known Activations