© 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. 30292
    Prev
    Next
    INDEX
    Explanations

    elevated spectator areas or stages

    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
     Inside
    -0.11
     aver
    -0.11
     Internal
    -0.10
     outdoors
    -0.10
     internally
    -0.10
     neigh
    -0.10
     indoors
    -0.10
     inside
    -0.09
    Inside
    -0.09
     tracker
    -0.09
    POSITIVE LOGITS
     backstage
    0.20
     podium
    0.20
     balcony
    0.19
     balcon
    0.18
     sidelines
    0.18
     raised
    0.16
     Raised
    0.16
    Raised
    0.16
     elevated
    0.16
     spectators
    0.15
    Activations Density 0.183%

    No Known Activations